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 Claims
This action is in reply to an application filed on 09/11/2025. Claims 1-16 and 18-20 are currently pending and have been examined.
Drawings
Figures 1-3 are objected to because they are of insufficient quality that would not allow for infinite reproduction. The Examiner suggests the Applicant change the drawings to simply black and white and eliminate the greyscale to make the drawings clearer. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 14 and 15 are rejected under 35 U.S.C. 112(a) as failing to comply with the written description requirement. The claims contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor at the time the application was filed, had possession of the claimed invention.
The disclosed embodiments
The specification discloses five models, illustrated in Figs. 3a to 3e and summarized in Table 1 at ¶¶ [00122]-[00123]:
Figure
Input parameters
No. of params
ROC-AUC
3a
Albumin value, Eosinophil value, Troponin value
3
0.80
3b
+ second Troponin value; rate of change of Tn concentration
5
0.81
3c
+ average body temperature; MCHC; Hemoglobin
8
0.83
3d
+ C-reactive protein; Hematocrit; minimum body temperature; average diastolic blood pressure
12
0.84
3e
+ Eosinophil fraction; minimum diastolic blood pressure; minimum Tn; D-Dimer; Lymphocyte; age; maximum body weight; BUN; RDW
21
0.84
Claim 14 — members recited but not described
Claim 14 recites a Markush group of twenty-two parameters. Of these, the following appear nowhere in the specification other than within the corresponding list recitations, are never described, and are used in none of the models of Figs. 3a-3e: MDW (Monocyte Distribution Width), race, gender, oxygen saturation, white blood count (WBC), red blood count (RBC), and systolic blood pressure. The specification therefore does not reasonably convey possession of the invention as to those members. See MPEP § 2163; Ariad Pharms., Inc. v. Eli Lilly & Co., 598 F.3d 1336, 1351 (Fed. Cir. 2010) (en banc).
Claim 15 — scope beyond the disclosed sequence
Claim 15 permits "selecting at least one" parameter from a group of twenty-two and computing the indicator on that basis. The specification discloses only a fixed additive sequence in which parameters are added in groups (¶ [00122]), and never demonstrates the addition of any single parameter to the three-analyte base of Fig. 3a. The claim is accordingly broader than the disclosure supports.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 2, 3, 7, 13-16, 18, and 19 are rejected under 35 U.S.C. 112(b) as indefinite.
Claim 2 — "the plurality of AMI classes"
Claim 2 recites "the plurality of AMI classes." The only antecedent is "a plurality of AMI type classes," recited earlier in the same claim. The inconsistent terminology renders the recitation indefinite.
Claims 2 and 3 — overlapping scope
Claim 2 recites classifying the subject into classes "of subjects suspected of having" type 1 and type 2 AMI. Claim 3 recites classifying into classes "of subjects having" type 1 and type 2 AMI. Both depend from claim 1. It cannot be determined whether the two claims are intended to differ in scope, or how. Clarification is required.
Claim 7 — grammar and antecedent
(1) "based on a single or a plurality of Troponin value as input data" is grammatically inconsistent and it cannot be determined how many Troponin values are required.
(2) Claim 7 recites "at least one machine learning model of the computing device," while parent claim 5 has already recited "at least one machine learning model." It cannot be determined whether the same model or an additional model is intended.
Claim 13 — typographical error and antecedent basis
(1) Claim 13 recites "the at least one AMTI type indicator." Correction to "AMI" is required.
(2) Claim 13 recites computing "based on one or more of the maximum Troponin value, the determined rate of change of the Troponin concentration, the at least one Albumin value, and the at least one Eosinophil value." Parent claim 12 requires determining only "one or more of" a maximum value, a minimum value, a most recent value and a rate of change. Where a practitioner determines, for example, only the minimum Troponin value, the recitations of "the maximum Troponin value" and "the determined rate of change" in claim 13 lack antecedent basis.
Claim 14 — Markush members outside the recited category
Claim 14 recites "at least one further hematology, vital and/or laboratory parameter selected from the group consisting of MCHC …, age, gender, race, Lymphocyte, …." Age, gender and race are demographic attributes and are not hematology parameters, vital signs or laboratory parameters. The recited group therefore contains members inconsistent with the category the claim defines, and the scope cannot be determined. It is further unclear whether "Lymphocyte," which names a cell type rather than a measured quantity, refers to a count, a percentage or a concentration.
Claim 15 — internal contradiction, undefined abbreviation, improper Markush form
(1) Internal contradiction. Claim 15 requires "selecting at least one further hematology, vital and/or laboratory parameter," yet the recited group includes "maximum Tn value," "rate of change of the Tn concentration or value," "Minimum Tn value" and "Most recent Tn value." Troponin-derived values are not "further" parameters, claim 1 already requiring at least one Troponin value. It cannot be determined whether selection of a Troponin-derived value satisfies the limitation.
(2) "Tn." The abbreviation is not defined in the claims, which elsewhere recite "Troponin." The inconsistent terminology is indefinite.
(3) "Age value" is recited within a group defined as hematology, vital and/or laboratory parameters, for the reasons given in Part E.
(4) Markush form. "[S]elected among the group of parameters consisting of" is improper. The accepted form is "selected from the group consisting of." See MPEP § 2117.
Claims 16 and 18 — "steps of the method"
Claim 16 recites a computing device "configured to carry out steps of the method according to claim 1," and claim 18 recites instructions that "perform steps of the method according to claim 1." It cannot be determined which steps, or how many, are required. Amendment to "all of the steps of" or "the steps of" is required.
Claim 19 — garbled recitation
Claim 19 recites "computing the at least one type one AMI type indicator." No "type one AMI type indicator" has been previously recited; parent claim 4 recites "the at least one AMI type indicator." The recitation lacks antecedent basis and is indefinite..
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 16 and 18 are rejected under 35 U.S.C. 112(d) as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Claim 16 is directed to a computing device and claim 18 to a non-transitory computer-readable medium, yet each is written in dependent form referring to claim 1, which is directed to a method When, as here, an independent claim recites a particular method, a dependent claim drawn to a computer-readable medium capable of performing the method of the independent claim and/or a dependent claim drawn to a computing device are not a proper dependent claim, since the dependent claim could conceivably be infringed by mere possession of the computer program on a computer-readable medium and/or the computing device without performing any particular method steps at all, thereby infringing the dependent claim without necessarily infringing the independent claim, in violation of the infringement test for proper dependency of claims. See MPEP § 608.01(n)(III). Applicant may cancel the claims, amend the claims to place the claim in proper dependent form, rewrite the claims in independent form, or present a sufficient showing that the dependent claims comply with the statutory requirements.
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 1-16 and 18-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to a judicial exception without significantly more.
Step 1 — Statutory category
Claims 1-15 and 19-20 recite a series of steps and are directed to a process. Claim 16 is directed to a machine. Claim 18 recites a non-transitory computer-readable medium and is directed to an article of manufacture; no rejection is made under In re Nuijten. The analysis proceeds to Step 2A.
Step 2A, Prong One — The claims recite a judicial exception
Claim 1 recites obtaining, for a subject suspected of having AMI, at least one Troponin value, at least one Albumin value and at least one Eosinophil value, and "computing … at least one AMI type indicator indicative of one or both a likelihood for the subject to have a type 1 AMI and a likelihood for the subject to have a type 2 AMI."
The relationship between the concentrations of these three blood analytes and whether a subject's myocardial infarction is of type 1 or type 2 is a law of nature — a consequence of the underlying pathophysiology, which exists independently of any human action. A claim that recites the application of such a correlation to determine a patient's condition is directed to that natural relationship. See Mayo Collaborative Servs. v. Prometheus Labs., Inc., 566 U.S. 66, 77-79 (2012); Cleveland Clinic Found. v. True Health Diagnostics LLC, 859 F.3d 1352, 1361-62 (Fed. Cir. 2017) (claims correlating a blood biomarker to cardiovascular disease held ineligible); Athena Diagnostics, Inc. v. Mayo Collaborative Servs., 915 F.3d 743, 750-53 (Fed. Cir. 2019).
The computing step additionally recites a mental process. Evaluating three laboratory values and forming a judgment as to which type of infarction a patient has is an evaluation and judgment of the kind a clinician performs, and is practically performable in the human mind. See MPEP § 2106.04(a)(2)(III).
Mathematical concepts — claim 6. Claim 1 does not recite a mathematical relationship, calculation, formula or equation, and the mathematical concepts grouping is not relied upon as to claim 1. Claim 6, however, recites "a trained logistic regression, a trained random forest, a trained gradient boosting algorithm, and a trained artificial neural network," naming particular mathematical models, and additionally recites a mathematical concept under MPEP § 2106.04(a)(2)(I).
Step 2A, Prong Two — No integration into a practical application
(a) Apply it. The additional elements are "a computing device," "at least one processor," "at least one machine learning model" and, in claim 18, a non-transitory medium. Claim 1 recites computing "with the computing device," which is the recitation of a generic computer applied to the exception. See MPEP § 2106.05(f).
(b) Data gathering. The step of "obtaining … subject data" comprising the three analyte values is mere data gathering necessary to apply the correlation, and is insignificant extra-solution activity. See MPEP § 2106.05(g); Mayo, 566 U.S. at 79 (the "determining" step "tells doctors to engage in well-understood, routine, conventional activity previously engaged in by scientists in the field").
(c) No particular treatment or prophylaxis. No claim recites administering any therapy, performing any procedure, or taking any other action upon the subject. Every claim terminates in the computation or output of an indicator. MPEP § 2106.04(d)(2) is therefore not satisfied, and the claims fall on the Cleveland Clinic side of the line rather than the Vanda side. Compare Vanda Pharms. Inc. v. West-Ward Pharms. Int'l Ltd., 887 F.3d 1117, 1135-36 (Fed. Cir. 2018).
(d) Applicant's own characterization. The specification confirms the absence of integration. At ¶ [0019] the specification states: "It is emphasized that the computer-implemented method and device described herein relates to a data processing means for clinical decision support, and does not involve in and for itself any diagnostic or therapeutic activity." Applicant has thus expressly characterized the claimed subject matter as data processing that involves no diagnostic or therapeutic activity.
Step 2B — No inventive concept
The additional elements, considered individually and as an ordered combination, do not amount to significantly more. Generic computer implementation does not supply an inventive concept. MPEP § 2106.05(f).
The data-gathering step is well-understood, routine and conventional. Troponin, albumin and eosinophil determinations are among the laboratory values routinely obtained from patients presenting with chest pain, as evidenced by CN '011, whose chest-pain diagnostic model draws its feature variables from a routine panel expressly including "troponin T … serum albumin" (claim 5) and "eosinophil" (claim 6). See Berkheimer v. HP Inc., 881 F.3d 1360 (Fed. Cir. 2018); MPEP § 2106.05(d)(II).
Dependent claims
The dependent claims do not alter the analysis. Claims 2-4 and 19-20 recite further characterizations of the computed indicator, which are further evaluations within the exception. Claims 5-7 recite generic machine learning models. Claims 8-13 recite obtaining additional Troponin values and determining maxima, minima and rates of change, which are additional data gathering and mathematical operations. Claims 14-15 recite additional data to be gathered. Claims 16 and 18 recite generic hardware. None of these dependent claims provides integration of the judicial exception from the independent claims into a practical application. Furthermore, they do not amount to significantly more.
Conclusion
Claims 1-13 are directed to an abstract idea without significantly more and are rejected under 35 U.S.C. § 101. Claim 13 is separately rejected as 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 1-3, 5-16, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Than MP, Pickering JW, Sandoval Y, Shah ASV, Tsanas A, Apple FS, Blankenberg S, Cullen L, Mueller C, Neumann JT, Twerenbold R, Westermann D, Beshiri A, Mills NL; MI3 Collaborative. Machine Learning to Predict the Likelihood of Acute Myocardial Infarction. Circulation. 2019 Sep 10;140(11):899-909 in view of Chaudhuri, et al. (US 2023/0215563 A1) in further view of Zhu, et al. (CN 109585011).
With regards to claim 1, Than teaches a computer-implemented method of determining an acute myocardial infarction, AMI, type indicator (see at least page 899, a machine learning algorithm, the myocardial-ischaemic-injury-index (MI3), implemented on a computer and applied to determine whether a patient has type 1 myocardial infarction), the method comprising: obtaining, at a computing device, subject data associated with a subject suspected of having AMI (see at least page 899, MI3 "was trained on 3013 patients and tested on 7998 patients with SUSPECTED MYOCARDIAL INFARCTION," the algorithm receiving each patient's data as input), the subject data comprising: a) at least one Troponin value indicative of a Troponin concentration determined for the subject (see at least page 899, "[MI3] incorporating age, sex, and PAIRED HIGH-SENSITIVITY CARDIAC TROPONIN I CONCENTRATIONS."), …and computing, based on the obtained subject data with the computing device, at least one AMI type indicator (see at least page 899, "MI3 uses GRADIENT BOOSTING to COMPUTE A VALUE (0-100)") indicative of one or both a likelihood for the subject to have a type 1 AMI and a likelihood for the subject to have a type 2 AMI (see at least page 899, The value reflects "an individual's LIKELIHOOD OF A DIAGNOSIS OF TYPE 1 MYOCARDIAL INFARCTION.").
Than does not explicitly teach …b) at least one Albumin value indicative of an Albumin concentration determined for the subject, c) at least one Eosinophil value indicative of an Eosinophil concentration determined for the subject.
Chaudhuri teaches …b) at least one Albumin value indicative of an Albumin concentration determined for the subject (see at least ¶ 0044, feature values extractor specifically extracts values for albumin).
Zhu teaches …c) at least one Eosinophil value indicative of an Eosinophil concentration determined for the subject (see at least ¶ 10, eosinophils).
Than discloses the claimed method but for two of the three recited analytes. Its MI3 algorithm obtains Troponin values from a patient with suspected myocardial infarction, applies a trained model, and computes a value reflecting "an individual's likelihood of a diagnosis of type 1 myocardial infarction." Claim 1 requires an indicator "indicative of one or both a likelihood for the subject to have a type 1 AMI and a likelihood for the subject to have a type 2 AMI"; the recitation is disjunctive, and THAN's type 1 likelihood satisfies it. What THAN does not take as input is Albumin or Eosinophil.
Than itself invites the addition of further variables. Its stated premise is that "[v]ariations in cardiac troponin concentrations by age, sex, and time between samples in patients with suspected myocardial infarction are not currently accounted for in diagnostic approaches," and its stated approach is "to combine these variables through machine learning to improve the assessment of risk for individual patients." Than thus teaches that Troponin alone is an incomplete basis for individualized assessment and that the remedy is to combine Troponin with further patient variables in a machine learning model. Than combined it with age and sex. The method is expandable by design, and THAN supplies the reason to expand it.
Chaudhuri identifies Albumin as such a variable, in the same patient population. Chaudhuri builds machine learning models for acute myocardial infarction patients from electronic health record data, the AMI patient being "identified using a working diagnosis and/or an elevated troponin level" — the same population Than addresses. Its feature values extractor "specifically extracts values for the following features: BNP, BUN having positive impact, albumin, hemoglobin, sodium and chloride groups, age of patient…," and the laboratory tests it considers "may include: albumin… sodium level, troponin, wbc, weight …." Chaudhuri therefore establishes that in precisely Than's population, Albumin is present in the record alongside Troponin and is used as a model feature.
Zhu identifies Eosinophil in the same acute presentation. It discloses a random-forest diagnostic model for patients presenting with chest pain — the presentation from which patients with suspected myocardial infarction are drawn — and recites Eosinophil among the feature variables of that model.
One of ordinary skill following Than's teaching to combine Troponin with further patient variables would have looked to variables already collected from the same patients and already used as model features by others working in the same setting. Chaudhuri and Zhu identify two such variables. The modification supplies two additional numerical laboratory values to a model that already accepts numerical laboratory values, in a population from which both are routinely drawn, and therefore carries a reasonable expectation of success. This is the combination of prior art elements according to known methods, and the use of a known technique to improve a similar method in the same way, to yield predictable results. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 416-17 (2007); MPEP § 2143(A), (C), (D).
Claim 1 does not require the added analytes to contribute any particular discriminatory power. It requires only that the subject data comprise the Troponin, Albumin and Eosinophil values, and that the indicator be computed "based on the obtained subject data." A model of the kind Than discloses, operating on a feature set that includes Albumin per Chaudhuri and Eosinophil per Zhu, reads on the claim irrespective of the weight the model assigns to either.
All three references are analogous art. Each is a computer-implemented model that predicts a clinical state in acute cardiac patients from routinely collected laboratory data, and each addresses the same problem of extracting individualized assessment from an incomplete set of laboratory measurements. In re Klein, 647 F.3d 1343, 1348 (Fed. Cir. 2011); MPEP § 2141.01(a).
Applicant's own results confirm an ordinary rather than an unexpected outcome. The three claimed analytes yield an ROC-AUC of 0.80 (¶ [00123], Table 1), and the addition of eighteen further parameters raises it only to 0.84, with no improvement at all between the twelve-parameter and twenty-one-parameter models.
With regards to claim 2, Than teaches the method according to claim 1, wherein computing the at least one AMI type indicator further comprises: classifying, by using the subject data, the subject into at least one AMI type class of a plurality of AMI type classes, the plurality of AMI classes, comprising a type 1 AMI class of subjects suspected of having type 1 AMI and a type 2 AMI class of subjects suspected of having type 2 AMI (see at least page 899, MI3 "was trained on 3013 patients and tested on 7998 patients with SUSPECTED MYOCARDIAL INFARCTION", "MI3 uses GRADIENT BOOSTING to COMPUTE A VALUE (0-100)", The value reflects "an individual's LIKELIHOOD OF A DIAGNOSIS OF TYPE 1 MYOCARDIAL INFARCTION." [classifying]).
With regards to claim 3, Than teaches the method according to claim 1, wherein the at least one AMI type indicator is indicative of a classification result of classifying the subject into at least one of a type 1 AMI class of subjects having type 1 AMI and a type 2 AMI class of subjects having type 2 AMI (see at least page 899, "MI3 uses GRADIENT BOOSTING to COMPUTE A VALUE (0-100)", The value reflects "an individual's LIKELIHOOD OF A DIAGNOSIS OF TYPE 1 MYOCARDIAL INFARCTION." [classification]).
With regards to claim 5, Than teaches the method according to claim 1, wherein computing the at least one AMI type indicator is based on at least one machine learning model configured to receive and process input data associated with at least a subset of the subject data (see at least page 899, MI3 "was trained on 3013 patients and tested on 7998 patients with SUSPECTED MYOCARDIAL INFARCTION," the algorithm receiving each patient's data as input, "[MI3] incorporating age, sex, and PAIRED HIGH-SENSITIVITY CARDIAC TROPONIN I CONCENTRATIONS", "MI3 uses GRADIENT BOOSTING to COMPUTE A VALUE (0-100)"), The value reflects "an individual's LIKELIHOOD OF A DIAGNOSIS OF TYPE 1 MYOCARDIAL INFARCTION.").
With regards to claim 6, Than teaches the method according to claim 5, wherein the at least one machine learning model comprises one or more of a trained logistic regression, a trained random forest, a trained gradient boosting algorithm, and a trained artificial neural network (see at least page 899, "MI3 uses GRADIENT BOOSTING”).
With regards to claim 7, Than teaches the method according to claim 5, wherein the at least one AMI type indicator is computed based on at least one machine learning model of the computing device configured to compute the at least one AMI type indicator based on a single or a plurality of Troponin value as input data (see at least page 899, MI3 "was trained on 3013 patients and tested on 7998 patients with SUSPECTED MYOCARDIAL INFARCTION," the algorithm receiving each patient's data as input, "[MI3] incorporating age, sex, and PAIRED HIGH-SENSITIVITY CARDIAC TROPONIN I CONCENTRATIONS", "MI3 uses GRADIENT BOOSTING to COMPUTE A VALUE (0-100)"), The value reflects "an individual's LIKELIHOOD OF A DIAGNOSIS OF TYPE 1 MYOCARDIAL INFARCTION.").
With regards to claim 8, Than teaches the method according to claim 1, wherein obtaining the subject data includes: obtaining a first Troponin value indicative of a first Troponin concentration determined for the subject at a first time; and obtaining a second Troponin value for the subject indicative of a second Troponin concentration determined for the subject at a second time different than the first time; and wherein the AMI type indicator is computed based on the first Troponin value and based on the second Troponin value (see at least page 900, right column under “Study Design”, “MI3 incorporates age, sex, paired cardiac troponin I concentrations at presentation and at another early, yet flexible, time point, and rate of change of cardiac troponin I concentration).
With regards to claim 9, Than teaches the method according to claim 8, further comprising: determining a …Troponin value among the obtained first Troponin value and second Troponin value; wherein the AMI type indicator is computed based on the determined …Troponin value (see at least page 899, MI3 "was trained on 3013 patients and tested on 7998 patients with SUSPECTED MYOCARDIAL INFARCTION," the algorithm receiving each patient's data as input, "[MI3] incorporating age, sex, and PAIRED HIGH-SENSITIVITY CARDIAC TROPONIN I CONCENTRATIONS", "MI3 uses GRADIENT BOOSTING to COMPUTE A VALUE (0-100)"), The value reflects "an individual's LIKELIHOOD OF A DIAGNOSIS OF TYPE 1 MYOCARDIAL INFARCTION.")
Furthermore, Chaudhuri teaches …maximum (see at least ¶ 0104, maximum troponin value). The motivation to combine Chaudhuri with Than is the same as in claim 1 above.
With regards to claim 10, Than teaches the method according to claim 8, further comprising: determining a …Troponin value among the first Troponin value and second Troponin value; wherein the AMI type indicator is computed based on the determined …Troponin value (see at least page 899, MI3 "was trained on 3013 patients and tested on 7998 patients with SUSPECTED MYOCARDIAL INFARCTION," the algorithm receiving each patient's data as input, "[MI3] incorporating age, sex, and PAIRED HIGH-SENSITIVITY CARDIAC TROPONIN I CONCENTRATIONS", "MI3 uses GRADIENT BOOSTING to COMPUTE A VALUE (0-100)"), The value reflects "an individual's LIKELIHOOD OF A DIAGNOSIS OF TYPE 1 MYOCARDIAL INFARCTION.")
Furthermore, Chaudhuri teaches … minimum (see at least ¶ 0105, minimum troponin value). The motivation to combine Chaudhuri with Than is the same as in claim 1 above.
With regards to claim 11, Than teaches the method according to claim 8, further comprising: determining a rate of change of the Troponin concentration based on the first Troponin value and second Troponin value; and wherein the AMI type indicator is computed based on the determined rate of change of the Troponin concentration (see at least page 900, right column under “Study Design”, “MI3 incorporates …rate of change of cardiac troponin I concentration).
With regards to claim 12, Than teaches the method according to claim 1, wherein the subject data is indicative of a plurality of Troponin values determined for the subject at different times (see at least page 900, right column under “Study Design”, “MI3 incorporates age, sex, paired cardiac troponin I concentrations at presentation and at another early, yet flexible, time point); wherein the method further comprises: determining one or more of a maximum Troponin value of the plurality of obtained Troponin values, a minimum Troponin value of the plurality of obtained Troponin values, a most recent value of the plurality of Troponin values, and a rate of change of the Troponin concentration (see at least page 900, right column under “Study Design”, “MI3 incorporates …rate of change of cardiac troponin I concentration).
With regards to claim 13, Than teaches the method according to claim 12, wherein computing the at least one AMTI type indicator is based on one or more of the maximum Troponin value, the determined rate of change of the Troponin concentration, the at least one Albumin value, and the at least one Eosinophil value (see at least page 900, right column under “Study Design”, “MI3 incorporates …rate of change of cardiac troponin I concentration).
With regards to claim 14, Than teaches the method according to claim 1, wherein the subject data is indicative of at least one further hematology, vital and/or laboratory parameter selected from the group consisting of MCHC (mean corpuscular hemoglobin concentration), age, gender, race, Lymphocyte, diastolic blood pressure, systolic blood pressure value, oxygen saturation, red blood count (RBC), white blood count (WBC), respiratory rate, minimum respiratory rate, maximum respiratory rate, hemoglobin, Blood Urea Nitrogen (BUN), C-Reactive Protein (CRP), body temperature, minimum body temperature, maximum body temperature, hematocrit, Red Cell Distribution Width (RDW), Monocyte Distribution Width (MDW) (see at least page 899, "[MI3] incorporating age, sex”.
With regards to claim 15, Than teaches the method according to claim 1, further comprising: selecting at least one further hematology, vital and/or laboratory parameter, and computing the at least one AMI type indicator based on the selected at least one further hematology, vital and/or laboratory parameter, selected among the group of parameters consisting of:- maximum Tn value;- rate of change of the Tn concentration or value;- MCHC value;- Age value;- Minimum diastolic blood pressure value;- Average diastolic blood pressure value;- Minimum body temperature value;- Average body temperature value;- Minimum Tn value;- Red blood count;- Minimum respiratory rate;- Most recent Tn value;- C-reactive protein;- Lymphocytes fraction; - BUN; - Lymphocyte count or value; - Hematocrit value; - Body weight; - Maximum body weight; - D-dimer; - Hemoglobin value; and – RDW (see at least page 900, right column under “Study Design”, “MI3 incorporates age, sex, paired cardiac troponin I concentrations at presentation and at another early, yet flexible, time point, and rate of change of cardiac troponin I concentration).
With regards to claim 16, Than teaches the computing device including one or more processors for data processing, wherein the computing device is configured to carry out steps of the method according to claim 1 (see at least figure 4, MI3 presented on a smartphone [computing device with processor]).
With regards to claim 18, Than teaches the non-transitory computer-readable medium storing a computer program which, when executed by one or more processors of a computing device, instructs the computing device to perform steps of the method according to claim 1 (see at least figure 4, MI3 presented on a smartphone [computing device with processor and computer-readable medium storing a computer program to execute on smartphone]).
Claims 4, 19, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Than MP, Pickering JW, Sandoval Y, Shah ASV, Tsanas A, Apple FS, Blankenberg S, Cullen L, Mueller C, Neumann JT, Twerenbold R, Westermann D, Beshiri A, Mills NL; MI3 Collaborative. Machine Learning to Predict the Likelihood of Acute Myocardial Infarction. Circulation. 2019 Sep 10;140(11):899-909 in view of Chaudhuri, et al. (US 2023/0215563 A1) in further view of Zhu, et al. (CN 109585011) in further view of Neumann JT, Weimann J, Sörensen NA, Hartikainen TS, Haller PM, Lehmacher J, et al., "A Biomarker Model to Distinguish Types of Myocardial Infarction and Injury," JACC, vol. 78 (Aug. 1, 2021).
With regards to claim 4, Than does not explicitly teach the method according to claim 1, wherein computing the at least one AMI type indicator includes: computing the likelihood for the subject to have type 1 AMI and the likelihood for the subject to have type 2 AMI. Neumann teaches the method according to claim 1, wherein computing the at least one AMI type indicator includes: computing the likelihood for the subject to have type 1 AMI and the likelihood for the subject to have type 2 AMI (see at least page 781, “Methods”, “Results”, using a model and biomarkers to discriminate between T1MI and T2MI; page 781, right column – page 782, left column, discriminating between T1MI and T2MI in individual patients).
Than computes, for a patient with suspected myocardial infarction, "a value (0-100) reflecting an individual's likelihood of a diagnosis of type 1 myocardial infarction," using gradient boosting over age, sex and paired high-sensitivity cardiac troponin I concentrations. Than thus resolves whether a patient is likely to have type 1 myocardial infarction. It does not resolve what is true of the patient who is not — whether that patient has type 2 myocardial infarction or some other myocardial injury.
Neumann identifies that precise gap as the problem to be solved, opening: "Discrimination among patients with type 1 myocardial infarction (T1MI), type 2 myocardial infarction (T2MI), and myocardial injury is difficult." A practitioner applying THAN's MI3 in the emergency department confronts that residual question immediately, because THAN's output leaves it open.
Neumann then demonstrates that the same approach answers it. Working in the same setting — patients "presenting with suspected myocardial infarction" in an emergency department, with the final diagnosis "adjudicated on the basis of the fourth universal definition of MI" — Neumann applies "multivariable logistic regression analysis" over a 29-biomarker panel and reports that "4 biomarkers (apolipoprotein A-II, N-terminal prohormone of brain natriuretic peptide, copeptin, and high-sensitivity cardiac troponin I) remained significant discriminators between T1MI and T2MI," with an area under the curve of 0.82 on internal validation, concluding that "[r]egression models based on these biomarkers allowed good discrimination."
The two references are therefore not merely compatible but sequential: the same population, the same class of supervised model over blood analyte concentrations, the same reference standard, and the same objective of individualized assessment. Neumann extends to type 1 versus type 2 what Than performed for type 1. Moving from Than's output to the claimed indicator is a change in the training label, not in technique.
Than independently invites the modification. Its stated aim was "to combine these variables through machine learning to improve the assessment of risk for individual patients," its premise being that variations in troponin "are not currently accounted for in diagnostic approaches." Neumann confirms both halves of that premise for the type-discrimination problem: troponin is retained as a discriminator, but only alongside three further blood analytes, so troponin alone is insufficient and supplementation is required.
The claimed indicator follows directly. Claim 1 requires an indicator "indicative of one or both a likelihood for the subject to have a type 1 AMI and a likelihood for the subject to have a type 2 AMI." Than supplies the first; Neumann supplies a model discriminating between the two, from which the second follows. Applicant's own specification confirms the two are complementary, stating that "an indicator for AMI type 1 may also be computed as (100% − (%-likelihood for AMI type 2))." Computing one likelihood in a two-class discrimination therefore yields the other as a matter of arithmetic, and claims 4, 19 and 20 add nothing beyond that arithmetic.
A reasonable expectation of success is established by the references themselves. Each reports a validated model over blood analyte concentrations in this population — Than on 7,998 test patients, Neumann with internal validation by bootstrapping at an area under the curve of 0.82. This is the combination of prior art elements according to known methods, and the use of a known technique to improve a similar method in the same way, yielding predictable results. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 416-17 (2007); MPEP § 2143(A), (C), (D). Applicant's own results are consistent with an ordinary outcome: the claimed three-analyte model achieves an ROC-AUC of 0.80 (¶ [00123], Table 1), below what Neumann reports for the same discrimination.
With regards to claim 19, Than does not explicitly teach the method according to claim 4, wherein computing the at least one type one AMI type indicator includes comparing the likelihood for the subject to have type 1 AMI and the likelihood for the subject to have type 2 AMI with one another. Neumann teaches the method according to claim 4, wherein computing the at least one type one AMI type indicator includes comparing the likelihood for the subject to have type 1 AMI and the likelihood for the subject to have type 2 AMI with one another (see at least page 781, “Methods”, “Results”, using a model and biomarkers to discriminate [compare likelihood] between T1MI and T2MI; page 781, right column – page 782, left column, discriminating between T1MI and T2MI in individual patients).
The motivation to combine Neumann with Than is the same as in claim 4 above.
With regards to claim 20, Than does not explicitly teach the method according to claim 4, wherein the computed at least one AMI type indicator is indicative of a difference between the computed likelihood for type 1 AMI and the computed likelihood for type 2 AMI. Neumann teaches the method according to claim 4, wherein the computed at least one AMI type indicator is indicative of a difference between the computed likelihood for type 1 AMI and the computed likelihood for type 2 AMI (see at least page 781, “Methods”, “Results”, using a model and biomarkers to discriminate [difference] between T1MI and T2MI; page 781, right column – page 782, left column, discriminating between T1MI and T2MI in individual patients).
The motivation to combine Neumann with Than is the same as in claim 4 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Hazen, et al. (US 2009/0061472 A1) which discloses for methods characterizing the near term risk of experiencing a major adverse cardiac event in a patient presenting with chest pain are provided. In one embodiment the method comprises determining the level of myeloperoxidase (MPO) activity in a bodily sample obtained from the patient. In another embodiment, the method comprises determining the level of MPO mass in a bodily sample obtained from the patient. In another embodiment, the method comprises determining the level of one or more select MPO-generated oxidation products in a bodily sample obtained from the patient. The select MPO-generated oxidation products are dityrosine, nitrotyrosine, chlorotyrosine, methionine sulphoxide or an MPO-generated lipid peroxidation product. Levels of MPO activity, MPO mass, or the select MPO-generated oxidation product in bodily samples from the test subject are then compared to a control value that is derived from measurements of MPO activity, MPO mass, or the select MPO-generated oxidation product in comparable bodily samples obtained from control population. Such comparison can also be used to determine the near term treatment of the patient.
Liu R, Wang M, Zheng T, Zhang R, Li N, Chen Z, Yan H, Shi Q. An artificial intelligence-based risk prediction model of myocardial infarction. BMC Bioinformatics. 2022 Jun 7;23(1):217. doi: 10.1186/s12859-022-04761-4. PMID: 35672659; PMCID: PMC9175344 which discloses myocardial infarction can lead to malignant arrhythmia, heart failure, and sudden death. Clinical studies have shown that early identification of and timely intervention for acute MI can significantly reduce mortality. The traditional MI risk assessment models are subjective, and the data that go into them are difficult to obtain. Generally, the assessment is only conducted among high-risk patient groups. To construct an artificial intelligence–based risk prediction model of myocardial infarction (MI) for continuous and active monitoring of inpatients, especially those in non-cardiovascular departments, and early warning of MI.
Nestelberger T, Boeddinghaus J, Lopez-Ayala P, Kaier TE, Marber M, et al., APACE Investigators, "Cardiovascular Biomarkers in the Early Discrimination of Type 2 Myocardial Infarction," JAMA CARDIOLOGY (July 1, 2021), DOI 10.1001/jamacardio.2021.0669. which discloses rapid and accurate noninvasive discrimination of type 2 myocardial infarction (T2MI), which is because of a supply-demand mismatch, from type 1 myocardial infarction (T1MI), which arises via plaque rupture, is essential, because treatment differs substantially. Unfortunately, this is a major unmet clinical need, because even high-sensitivity cardiac troponin (hs-cTn) measurement provides only modest accuracy. To test the hypothesis that novel cardiovascular biomarkers quantifying different pathophysiological pathways involved in T2MI and/or T1MI may aid physicians in the rapid discrimination of T2MI vs T1MI
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Joey Burgess whose telephone number is (571)270-5547. The examiner can normally be reached Monday through Friday 9-6.
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, Kambiz Abdi can be reached on 571-272-6702 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.
/JOSEPH D BURGESS/ Primary Examiner, Art Unit 3685
