Method for assessing systemic inflammation

Abstract

The present invention relates to the field of diagnostics. In particular, it relates to a method for assessing systemic inflammation in a subject exhibiting symptoms thereof comprising a) determining in a sample of said subject the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6, ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMSlor iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3, b) comparing said determined amounts of biomarkers from said group of biomarkers to a reference, and c) assessing systemic inflammation in the subject. Further, the present invention, in general, relates to the use of the amounts of said biomarkers in a sample of a subject exhibiting symptoms of systemic inflammation for assessing systemic inflammation. Moreover, contemplated are a device and a kit for assessing systemic inflammation.

Description

[0001] Method for assessing systemic inflammation

[0002] The present invention relates to the field of diagnostics. In particular, it relates to a method for assessing systemic inflammation in a subject exhibiting symptoms thereof comprising a) determining in a sample of said subject the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6, ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMSlor iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3, b) comparing said determined amounts of biomarkers from said group of biomarkers to a reference, and c) assessing systemic inflammation in the subject. Further, the present invention, in general, relates to the use of the amounts of said biomarkers in a sample of a subject exhibiting symptoms of systemic inflammation for assessing systemic inflammation. Moreover, contemplated are a device and a kit for assessing systemic inflammation.

[0003] Sepsis is a life-threatening medical emergency that specifically may occur when the body's response to an infection causes damage on its own tissues. Thus, early diagnosis of sepsis and septic shock is crucial, in order to enable the healthcare personnel to respond to the respective situation rapidly. Several stages of sepsis are known, which, in the following, are also referred to as septic states, inflammatory states or systemic inflammatory states. Thus, the first stage or state is also referred to as “systemic inflammatory response syndrome (SIRS)”. In this stage, typically, one or more of the following symptoms may be noted: abnormal body temperature, abnormal heart rate, abnormal respiratory rate, abnormal blood gas, abnormal white blood cell count. In the second stage or stage, often referred to as “sepsis”, SIRS occurs in response to an infectious process. The third stage or state typically is referred to as “severe sepsis”. This third stage is typically defined as sepsis with sepsis- induced organ dysfunction or tissue hypoperfusion. In this third stage, typically, one or more of the following additional symptoms may occur: hypotension, elevated lactate, decreased urine output. Severe sepsis is an infectious disease state associated with multiple organ dysfunction syndrome (MODS). Finally, the fourth state or stage is referred to as “septic shock”. This fourth stage denotes a severe sepsis in conjunction with persistently low blood pressure. However, various criteria exist for differential diagnosis of the aforementioned systemic inflammation conditions.

[0004] Depending on the results of the diagnosis of the septic or systemic inflammatory state, treatment in the form of number of actions or “bundles” is given to the patient. Thus, administration of antibiotics, monitoring of blood cultures, monitoring of lactate, hemoglobin determination, urine output monitoring, administration of high-flow oxygen and administration of intravenous fluids are typical treatment measures. Further, depending on the stage, other measures are required, such as surgical drainage, support for organ dysfunction such as hemodialysis, mechanical lung ventilation, transfusions, drug and fluid therapy or combinations thereof. Besides choosing appropriate measures, timing of these measures, however, is a crucial factor for successful treatment.

[0005] Besides traditional detection of symptoms, such as one or more of the above-mentioned symptoms, indicating a systemic inflammatory state, the evaluation of the level of specific biomarkers gained from patient samples is known for detecting systemic inflammatory states. Thus, as an example, EP 3 011 059 Bl and WO 2014 / 201516 A2 discloses methods and apparatus for identifying biomarkers and in particular for identifying biomarkers for use in making clinical assessments, such as early diagnostic, diagnostic, disease stage, disease severity, disease subtype, response to therapy or prognostic assessments of, inter alia, patients suffering from, suspected of suffering from, or with clinical signs of SIRS (Systemic Inflammatory Response Syndrome) being either infection-negative SIRS or infection-positive SIRS. Further, evaluation of biomarker sets for sepsis assessment has been reported (see, e.g., Sweeney TE, Shidham A, Wong HR, Khatri P.: “A comprehensive time-course-based multicohort analysis of sepsis and sterile inflammation reveals a robust diagnostic gene set”, Sci Transl Med. 2015 May 13;7(287):287ra71. doi: 10.1126 / scitranslmed.aaa5993. PMID: 25972003; PMCID: PMC4734362.)

[0006] Despite the advantages implied by the above-mentioned means and methods, several challenges and room for improvement remain. For example, known methods and devices for diagnosis of sepsis are rather nonspecific and enable the healthcare personnel to simply distinguish two different classes of systemic inflammation, such as sepsis from septic shock. As noted above, however, precise diagnosis of the patient’s systemic inflammatory state may be crucial, in order to take appropriate and state-specific therapeutic measures, thereby increasing the efficiency of the treatment.

[0007] The technical problem underlying the present invention may be seen as the provision of means and methods for complying with the aforementioned needs. The technical problem is solved by the embodiments characterized in the claims and herein below.

[0008] Thus, the present invention relates to a method for assessing systemic inflammation in a subject exhibiting symptoms thereof comprising: a) determining in a sample of said subject the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3; b) comparing said determined amounts of biomarkers from said group of biomarkers to a reference; and c) assessing systemic inflammation in the subject.

[0009] It is to be understood that in the specification and in the claims, “a” or “an” can mean one or more, depending upon the context in which it is used. Thus, for example, reference to “an” item can mean that at least one item can be utilized.

[0010] As used in the following, the terms “have”, “comprise” or “include” may be meant to have a non-limiting meaning or a limiting meaning. Thus, having a limiting meaning these terms may refer to a situation in which, besides the feature introduced by these terms, no other features are present in an embodiment described, i.e. the terms have a limiting meaning in the sense of “consisting of’ or “essentially consisting of’. Having a non-limiting meaning, the terms refer to a situation where besides the feature introduced by these terms, one or more other features are present in an embodiment described. Further, as used in the following, the terms “preferably”, “more preferably”, “most preferably”, "particularly", "more particularly", “typically”, and “more typically” or similar terms are used in conjunction with additional or alternative features, without restricting alternative possibilities.

[0011] Further, it will be understood that the term “at least one” as used herein means that one or more of the items referred to following the term may be used in accordance with the invention. For example, if the term indicates that at least one item shall be used this may be understood as one item or more than one item, i.e. two, three, four, five or any other number. Depending on the item the term refers to the skilled person understands as to what upper limit the term may refer, if any.

[0012] The method according to the present invention may consist of the aforementioned steps (a) and (c) or may comprise further steps, such as pretreating or isolating the sample prior to step (a) and / or after step (c) further one or more steps of evaluating the determined biomarker, e.g., by comparing it to references in order to provide a diagnostic or prognostic, conclusion depending on the aim of the determination of the biomarker.

[0013] The term “assessing” as used herein refers to diagnosing systemic inflammation in a subject, differentiating between different types of systemic inflammation in a subject, preferably, differentiating between SIRS, sepsis and septic shock, or predicting systemic inflammation in a subject. As will be understood by those skilled in the art, an assessment is usually not intended to be correct for 100% of the subjects to be investigated. The term, however, requires that the assessment is correct for a statistically significant portion of the subjects (e.g. a cohort in a cohort study). Whether a portion is statistically significant can be determined without further ado by the person skilled in the art using various well known statistic evaluation tools, e.g., determination of confidence intervals, p-value determination, Student's t- test, Mann- Whitney test etc.. Details are found in Dowdy and Wearden, Statistics for Research, John Wiley & Sons, New York 1983. Preferred confidence intervals are at least 90%, at least 95%, at least 97%, at least 98% or at least 99 %. The p-values are, preferably, 0.1, 0.05, 0.01, 0.005, or 0.0001.

[0014] The term “systemic inflammation” as used herein refers to inflammation which affects the entire organism rather than bring a locally restricted inflammation. Systemic inflammation is, typically, characterized by systemic symptoms of inflammation. Such symptoms of systemic inflammation are described in the prior art and are known to the clinician. Typically, said symptoms for systemic inflammation are selected from the group consisting of hyperthermia or hypothermia, tachycardia, tachypnoea, leucocyte abnormalities, and organ failure. Typically, said systemic inflammation is SIRS, sepsis or septic shock (see Singer, 2016, JAMA 315(8): 801-810).

[0015] The term “SIRS” as used herein refers to systemic inflammation characterized in that at least two of the following symptoms occur: body temperature above 38°C or below 36°C; heart rate of at least 90 beats per minute; respiratory rate of at least 20 or PaCCh less than 32 mmHg; white blood cell count of at least 12,000 / mm3or less than 4,000 / mm3or at least 10% bands.

[0016] The term “sepsis” as used herein refers to systemic inflammation characterized in that the subject exhibits the symptoms of SIRS as specified above and suffers from or is suspected to suffer from infection. Moreover, severe forms of sepsis may also be accompanied by lactic acidose and SBP of less than 90 or SBP drop of 40 mmHG of normal or more.

[0017] The term “septic shock” as used herein refers to systemic inflammation characterized in that the subject exhibits the symptoms of sepsis or severe sepsis as specified before and hypotension despite of adequate fluid resuscitation, i.e. failure or severe impairment of the circulatory system.

[0018] The term “subject” as used herein relates to animals, preferably mammals, and, more preferably, humans. The subject according to the present invention shall exhibit symptoms of systemic inflammation as described elsewhere herein and / or shall be suffering from systemic inflammation. Moreover, the method of the present invention may be specifically applied for juvenile or adult subjects. Preferably, amounts of biomarkers from the second group of biomarkers are determined and wherein said subject is an adult subject. Yet, preferably, amounts of biomarkers from the third group of biomarkers are determined and wherein said subject is a juvenile subject. An adult subject as referred to herein has an age of at least 18 years. A juvenile subject as referred to herein has an age of 17 years or less.

[0019] The term “sample” refers, typically, to a sample of a body fluid. Said sample may be a blood sample such as a whole blood, serum or plasma sample. More specifically, said sample shall comprises leucocytes, preferably, peripheral blood mononuclear cells (PBMC). Samples of body fluids can be obtained by well-known techniques. The term “biomarker” as used in accordance with the present invention relates to the biomarker protein or any precursor protein, fragment or derivative thereof which is naturally generated and which reflects the amount of the biomarker protein. Moreover, the term also encompasses any nucleic acid molecule which reflects the amount of biomarker protein. Preferably, such transcribed nucleic acid molecules are the messenger RNA molecules (mRNA) or any precursor or variant thereof, including pre-mRNA or mRNA for splice variants. Those RNA nucleic acid molecules may be determined as biomarkers in accordance with the present invention as well. Thus, it will be understood that if, e.g., POMK shall be determined as biomarker in accordance with the present invention, either POMK protein may be determined or a transcribed nucleic acid molecule encoding POMK protein such as POMK mRNA. The same applies for the other specifically mentioned biomarkers referred to herein except specified otherwise. Preferably, the protein amount or RNA amount of the biomarkers is determined in accordance with the present invention.

[0020] The biomarkers of the first, second and third group as referred to herein are listed in the following Tables 1 to 3. The Tables indicate the abbreviations of the biomarkers, their full designation and an UniProt accession number for each biomarker which, preferably, shows the human amino acid sequence of the biomarker protein.

[0021] Table 1 : first group of biomarkers (all)

[0022] Table 2: Second group of biomarkers (adult)

[0023] Table 3: Third group of biomarkers (juvenile)

[0024]

[0025] It will be understood that for the method for assessing systemic inflammation in a subject, typically the amounts of all biomarkers from one group of biomarkers as cited above shall be determined. Which group of biomarkers to be assessed, may depend on various factors pertaining to the subject suffering from systemic inflammation, such as age, symptoms, and the like. The phrase “the amounts of the biomarkers from a group of biomarkers” as used in line with the present invention is hence specifically intended to specify that the amounts of all of the biomarkers listed as one group, i.e. all of the ten biomarkers in one of the groups, are meant.

[0026] For example, more typically, to differentiate between specific stages of systemic inflammation, e.g. SIRS, sepsis and septic shock, all ten biomarkers of the first group of biomarkers, i.e. POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6, shall be assessed. To assess systemic inflammation in adult subjects, preferably, all ten biomarkers of the second group of biomarkers as cited herein, i.e. NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1 may be used. It is further preferred that for the assessment of systemic inflammation in juvenile subjects, all ten biomarkers of the third group of biomarkers as cited herein, i.e. C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3, shall be used. It will be understood that biomarkers as referred to herein, in addition to those biomarkers having the specific sequence as deposited under the UniProt accession number also encompass variants of said proteins. Such variants have at least the same essential biological and immunological properties as the aforementioned proteins deposited under the respective UniProt accession numbers. In particular, they share the same essential biological and immunological properties if they are detectable by the same specific assays referred to in this specification. Moreover, it is to be understood that a variant as referred to in accordance with the present invention shall have an amino acid sequence which differs due to at least one amino acid substitution, deletion and / or addition wherein the amino acid sequence of the variant is still, preferably, at least 50%, 60%, 70%, 80%, 85%, 90%, 92%, 95%, 97%, 98%, or 99% identical with the specific amino sequence of the biomarker protein as deposited under the indicated UniProt accession number, preferably over the entire length of the said biomarker protein, respectively.

[0027] The degree of identity between two amino acid sequences in accordance with the present invention can be determined by algorithms well known in the art. Preferably, the degree of identity is to be determined by comparing two optimally aligned sequences over a comparison window, where the fragment of amino acid sequence in the comparison window may comprise additions or deletions (e.g., gaps or overhangs) as compared to the reference sequence (which does not comprise additions or deletions) for optimal alignment. The percentage is calculated by determining the number of positions at which the identical amino acid residue occurs in both sequences to yield the number of matched positions, dividing the number of matched positions by the total number of positions in the window of comparison and multiplying the result by 100 to yield the percentage of sequence identity. Optimal alignment of sequences for comparison may be conducted by the local homology algorithm disclosed by Smith, by the homology alignment algorithm of Needleman, by the search for similarity method of Pearson, by computerized implementations of these algorithms (GAP, BESTFIT, BLAST, FAST, PASTA, and TFASTA in the Wisconsin Genetics Software Package, Genetics Computer Group (GCG), 575 Science Dr., Madison, WI) or by visual inspection. Given that two sequences have been identified for comparison, GAP and BEST- FIT are preferably employed to determine their optimal alignment and, thus, the degree of identity. Preferably, the default values of 5.00 for gap weight and 0.30 for gap weight length are used. Variants referred to above may be allelic variants or any other species specific homologs, paralogs, or orthologs. Variants referred to above may be allelic variants or any other species specific homologs, paralogs, or orthologs. Determining the amount of one or more biomarker(s) as referred to in accordance with the present invention encompasses measuring the amount or concentration, preferably, semi- quantitatively or quantitatively.

[0028] Measuring may be carried out directly or indirectly. Direct measuring relates to measuring the amount or concentration of the biomarker based on a signal which is obtained from the biomarker molecule itself and the intensity of which directly correlates with the number of molecules of the biomarker present in the sample. Such a signal - sometimes referred to herein as intensity signal - may be obtained, e.g., by measuring an intensity value of a specific physical or chemical property of the biomarker molecule. Indirect measuring includes measuring of a signal obtained from a secondary component, i.e. a component not being the biomarker molecule itself.

[0029] In accordance with the present invention, determining the amount of a biomarker can be achieved by all known means for determining such amounts in a sample. Said means comprise immunoassay devices and methods which may utilize detection agents such as labeled molecules in various sandwich, competition, or other assay formats. Said assays will develop a signal which is indicative for the presence or absence of the peptide or polypeptide. Moreover, the signal strength can, preferably, be correlated directly or indirectly (e.g. reverseproportional) to the amount of the biomarker present in a sample. Further suitable methods comprise measuring a physical or chemical property specific for the biomarkers. Said methods comprise, preferably, biosensors, optical devices coupled to immunoassays, biochips, or other analytical devices such as chromatography devices or single cell analyzing devices such as FACS analyzers or devices for single cell PCR analysis.

[0030] Typically, determining the amount of a biomarker in line with the invention is performed in parallel to determining the amounts of further biomarkers of a group of biomarkers, for example a group of ten biomarkers.

[0031] Preferably, the biomarker(s) to be determined in accordance with the present invention may be determined as protein. To this end, typically a detection agent is applied that specifically binds to the said biomarker protein and that can be detected either by a detectable label present in the detection agent or by a secondary binding molecule that specifically binds to the detection agent and comprises a detectable label. The term “detection agent” as referred to in this context may be any molecule that is capable of specifically binding to the biomarker to be detected. Preferably, such a detection agent may be an antibody, an antibody mimetic or an aptamer.

[0032] An antibody in accordance with the present invention may encompass all types of antibodies which specifically bind to the biomarker protein. Preferably, the antibody of the present invention is a monoclonal antibody, a polyclonal antibody, a single chain antibody, a chimeric antibody or any fragment or derivative of such antibodies being still capable of binding to the biomarker protein specifically. Such fragments and derivatives comprised by the term antibody as used herein encompass a bispecific antibody, a synthetic antibody, a Fab, F(ab)2 Fv or scFv fragment, or a chemically modified derivative of any of these antibodies. Specific binding as used in the context of the anti-body of the present invention means that the antibody does not cross react with other molecules present in the sample to be investigated. Specific binding can be tested by various well-known techniques. Antibodies or fragments thereof, in general, can be obtained by using methods which are described in standard text books, e.g., in Harlow and Lane "Antibodies, A Laboratory Manual", CSH Press, Cold Spring Harbor, 1988. Monoclonal antibodies can be prepared by the techniques which comprise the fusion of mouse myeloma cells to spleen cells derived from immunized mammals and, preferably, immunized mice.

[0033] An antibody mimetic in accordance with the present invention encompasses peptide or protein molecules that have antibody-like binding properties but which are not structurally related to antibodies. Such antibody mimetics have typically a molecular weight of up to 20 kDa. Preferably, an antibody mimetic in accordance with the present invention may be an affibody molecule, an affilin, an affimer, an affitin, an alphabody, an anticalin, an avimer, an DARPin, a fynomer, a gastrobody, a Kunitz domain protein, a monobody, a nanoCLAMP, a repedody, a centryn or an obody.

[0034] An aptamer according to the present invention may be a nucleic acid or peptide aptamer. Specific aptamers can be generated by techniques well known in the art including, e.g., the systematic evolution of ligands by exponential enrichment (SELEX) technology. Peptide aptamers comprise of a variable peptide loop attached at both ends to a protein scaffold. This double structural constraint shall increase the binding affinity of the peptide aptamer into the nano-molar range. Said variable peptide loop length is, typically, composed of ten to twenty amino acids, and the scaffold may be any protein having improved solubility and compacity properties, such as thioredoxin-A. Peptide aptamer selection can be made using different systems including, e.g., the yeast two-hybrid system. The term also encompasses optimized or modified aptamers such as optimers, split aptamers or X-aptamers.

[0035] A detectable label as referred to herein which may be used in accordance with the invention include gold particles, latex beads, acridan ester, luminol, ruthenium, enzymatically active labels, radioactive labels, magnetic labels, e.g., magnetic beads, including paramagnetic and superparamagnetic labels, and fluorescent labels. Enzymatically active labels include e.g. horseradish peroxidase, alkaline phosphatase, beta-Galactosidase, Luciferase, and derivatives thereof. Suitable substrates for detection include di-amino-benzidine (DAB), 3,3'-5,5'- tetramethylbenzidine, NBT-BCIP (4-nitro blue tetrazolium chloride and 5-bromo-4-chloro- 3-indolyl-phosphate. A suitable enzyme-substrate combination may result in a colored reaction product, fluorescence or chemiluminescence, which can be measured according to methods known in the art (e.g. using a light-sensitive film or a suitable camera system). As for measuring the enzymatic reaction, the criteria given above apply analogously. Typical fluorescent labels include fluorescent proteins (such as GFP and its derivatives), Cy3, Cy5, Texas Red, Fluorescein, and the Alexa dyes. Also the use of quantum dots as fluorescent labels is contemplated. Typical radioactive labels include 35S, 1251, 32P, 33P and the like. A radioactive label can be detected by any method known and appropriate, e.g. a light-sensitive film or a phosphor imager. Suitable labels may also be or comprise tags, such as biotin, digoxygenin, His-, GST-, FLAG-, GFP-, MYC-tag, influenza A virus haemagglutinin (HA), maltose binding protein, and the like.

[0036] Also preferably, the biomarker(s) to be determined in accordance with the present invention may be determined as nucleic acid molecules, preferably, as transcripts such as mRNAs. If a transcript encoding a biomarker protein is to be detected, it will be understood that, typically, a nucleic acid molecule being either RNA or DNA may be used for detection as detection agent according to the invention.

[0037] Detection systems using nucleic acid as detection molecules can be based on complementary base pairing interactions. The recognition process is based on the principle of complementary nucleic acid base pairing. If the target nucleic acid sequence is known, complementary sequences can be synthesized and labeled for detection. The hybridization event can be detected by known measures. Moreover, using PCR-based techniques, even low amounts of transcripts can be determined and quantified. How to carry out such PCR-based techniques is well known to the skilled artisan. A nucleic acid molecule useful as a detection agent in accordance with the present invention refers to DNA or RNA molecules that are capable of specifically interacting with the transcript for the biomarker. The biomarker transcript is a nucleic acid molecule, too, and specific binding can be achieved via the specific interactions of complementary or reverse complementary nucleotide strands. Typically, the nucleic acid useful as detection agent is selected from the group consisting of an antisense RNA, a siRNA or a micro RNA. Also preferably, oligonucleotides having complementary and reverse complementary sequences may be used as target transcript specific primers for PCR-based detection techniques.

[0038] An antisense RNA as used herein refers to RNA which comprise a nucleic acid sequence which is essentially or perfectly complementary to the target transcript. Typically, an antisense nucleic acid molecule essentially consists of a nucleic acid sequence being complementary to at least 100 contiguous nucleotides, more preferably, at least 200, at least 300, at least 400 or at least 500 contiguous nucleotides of the target transcript. How to generate and use antisense nucleic acid molecules is well known in the art.

[0039] A siRNA as used herein refers to small interfering RNAs (siRNAs) which are complementary to target RNAs (encoding a gene of interest) and diminish or abolish gene expression by RNA interference (RNAi). RNAi is generally used to silence expression of a gene of interest by targeting mRNA. Briefly, the process of RNAi in the cell is initiated by double stranded RNAs (dsRNAs) which are cleaved by a ribonuclease, thus producing siRNA duplexes. The siRNA binds to another intracellular enzyme complex which is thereby activated to target whatever mRNA molecules are homologous (or complementary) to the siRNA sequence. The function of the complex is to target the homologous mRNA molecule through base pairing interactions between one of the siRNA strands and the target mRNA. Thus, siRNA molecules are capable of specific binding and can be used as detection agents according to the present invention. microRNA as used herein refers to a self-complementary single-stranded RNA which comprises a sense and an antisense strand linked via a hairpin structure. The micro RNA comprise a strand which is complementary to an RNA targeting sequences comprised by a transcript to be downregulated. micro RNAs are processed into smaller single stranded RNAs and, therefore, presumably also act via the RNAi mechanisms. How to design and to synthesize microRNAs which specifically bind and degrade a transcript of interest is known in the art. Due to the specific nucleic acid binding capabilities, they can be used as detection agents according to the invention as well. The term “amount” as used herein encompasses the absolute amount of the biomarker, the relative amount or concentration of the biomarker as well as any value or parameter which correlates thereto or can be derived therefrom. Such values or parameters comprise intensity signal values from all specific physical or chemical properties obtained from the said biomarker or a detection molecule and / or detectable label. It is to be understood that values correlating to the aforementioned amounts or parameters can also be obtained and / or modified by all standard mathematical operations.

[0040] Typically, the amount as referred to herein may be a normalized amount, i.e. an amount which is calculated based on the measured value for the amount of the biomarker and a normalizing parameter that allows for correction of physiological variability between different samples and / or technical variability caused by technical differences or irregularities between different measurements. Preferably, normalization for the measured amounts of the individual biomarkers in a test sample shall be made using measurements for said biomarkers in a one or more normalization sample(s) or a normalization value calculated on such measurements.

[0041] The determined amounts of the biomarkers are compared to a reference in accordance with the method of the present invention.

[0042] The term “reference” as used in accordance with the present invention relates to any amount or value which by comparison to the determined amount of the biomarker allows for assessing systemic inflammation in the subject. Thus, the reference amount or value may be obtained from a subject or a group of subjects known to suffer from systemic inflammation. In such a case, if similar amounts for the biomarkers are present in the test sample, the tested subject shall be assessed as suffering from systemic inflammation, whereas if amounts for the biomarkers which differ from the reference are determined in the test sample, the subject may be assessed as not suffering from systemic inflammation. The reference amount or value may also be obtained from a subject or a group of subjects known not to suffer from systemic inflammation. In such a case, if similar amounts for the biomarkers are present in the test sample, the tested subject shall be assessed as not suffering from systemic inflammation whereas if amounts for the biomarkers which differ from the reference are determined in the test sample, the subject may be assessed as suffering from systemic inflammation. More specifically, the method of the present invention when assessing systemic inflammation, preferably, comprises identifying whether the subject suffers from SIRS, sepsis or septic shock.

[0043] Typically, the reference may be derived from one or more subject(s) known to suffer from SIRS and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from SIRS whereas amounts that differ from the reference are indicative for a subject not suffering from SIRS. Also typically, the reference may be derived from one or more subject(s) known not to suffer from SIRS and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from SIRS.

[0044] Moreover, the reference may be, typically, derived from one or more subject(s) known to suffer from sepsis and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from sepsis whereas amounts that differ from the reference are indicative for a subject not suffering from sepsis. Also typically, the reference may be derived from one or more subject(s) known not to suffer from sepsis and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from sepsis.

[0045] Furthermore, the reference may be derived from one or more subject(s) known to suffer from septic shock and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from septic shock whereas amounts that differ from the reference are indicative for a subject not suffering from septic shock. Yet typically, the reference may be derived from one or more subject(s) known not to suffer from septic shock and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from septic shock.

[0046] The method of the present invention, typically, also comprises applying a regression analysis model for assessing systemic inflammation.

[0047] The term “regression analysis model” as used herein relates to any statistical process for estimating relationships between an outcome variable and one or more predictor variable(s). An outcome variable in accordance with the present invention may be systemic inflammation and, in particular, SIRS, sepsis or septic shock as a condition thereof. Predictor variables may be the abundance (i.e. the presence or absence or the amounts) of the biomarkers or the composition of the group of the said biomarkers. Typical regression models are linear regression models. However, also non-linear regression models may be used. The regression analysis model shall be a trained model which has been trained on labeled training patient data.

[0048] Training as used herein specifically may refer, without limitation, to a process of determining parameters of at least one machine learning and / or deep learning model, specifically of the algorithm of the machine learning and / or deep learning model, specifically on at least one training data set or set of training data. The training specifically may comprise at least one optimization or tuning process, wherein a best parameter combination, e.g. according to at least one optimization procedure, is determined. A trainable model as used herein, thus, may be or may comprise at least one mathematical model configured for transforming one or more input values into one or more output values by using one or more parameters which may be adjusted in order to enable the model to be trained. The trainable model specifically may be a trainable mathematical model which is trainable on at least one training data set using one or more of machine learning, deep learning, neural networks, or other form of artificial intelligence. The term specifically may refer, without limitation, to the fact that the trainable model can be further trained, optimized or updated based on additional training data. Specifically, the trainable model is trained on a training dataset. The trainable model may be trained by using machine learning. The trainable model may be at least partially data- driven by being trained on data from historical training data. The trainable model specifically may comprise at least one trainable model selected from the group consisting of: a decision tree model, specifically at least one of an XGBoost model and a Random Forest model; a Support Vector Machine (SVM) model, specifically, a linear kernel SVM; a nearest neighbors model, specifically a KNeighbors Classifier; a Bayes model, specifically a Gaussi- anNB() model; a regression model, specifically at least one of a LogisticRegression; a linear and a nonlinear regression model, e.g. a regression model comprising transformed features, such as log-transformed or polynomial; an Artificial Neural Network (ANN), specifically a non-linear Artificial Neural Network (ANN), in particular a deep learning architecture such as Convolutional NN, Recurrent NN, Long Short Term Memory NN, and the like; a kernelbased method; a tree regression model; a distributed gradient-boosting framework model, specifically a light gradient-boosting machine model (LightGBM classifier).

[0049] Consequently, a trained regression model as used herein may refer, without limitation, to a trainable model which has gone through at least one training process as defined above, by applying, at least once, a set of training data to the trainable model. Specifically, one or more parameters of the trainable model might have been adapted, on the basis of the training data, in order to transform the trainable model into a trained model. Specifically, the trained model may be a trainable model which was trained on at least one training dataset, also denoted training data. The trained model specifically may be or may comprise a classifier, configured for classifying an object, on the basis of one or more input variables, describing the object. The trained model specifically may comprise at least one trained model selected from the group consisting of a decision tree model, specifically at least one of an XGBoost model and a Random Forest model; a Support Vector Machine (SVM) model, specifically, a linear kernel SVM; a nearest neighbors model, specifically a KNeighbors Classifier; a Bayes model, specifically a GaussianNB() model; a regression model, specifically at least one of a LogisticRegression; a linear and a nonlinear regression model, e.g. a regression model comprising transformed features, such as log-transformed or polynomial; an Artificial Neural Network (ANN), specifically a non-linear Artificial Neural Network (ANN), in particular a deep learning architecture such as Convolutional NN, Recurrent NN, Long Short Term Memory NN, and the like; a kernel-based method; a tree regression model; a distributed gradient-boosting framework model, specifically a light gradient-boosting machine model (LightGBM classifier).

[0050] The trainable model and / or the trained model specifically may be a model taken from a software library, providing a plurality of trainable models. As an example, the Scikit-learn open- source software library may be mentioned, for trainable models and / or trained models being programmed in the Python programming language. Additionally or alternatively, also, as an example, reference may be made to the extreme Gradient Boosting (XGBoost) open-source software library, specifically providing gradient boosting trainable models, being programmed in one or more of the programming languages C++, Java, Python, R, Julia, Perl and Scala. Other libraries, however, are also feasible, as well as customized trainable models not retrieved from software libraries.

[0051] Labeled as used herein may refer, without limitation, to the property of training data having, besides the actual training data, additional information indicating a classification of the data. Thus, as an example, the labeled training patient data may contain, specifically for each subject or each data set of a subject, besides the abundance of the biomarkers, an indication of the known status of systemic inflammation. Thus, as an example, for each subject or each data set thereof, information may be comprised, indicating whether the subject is suffering from systemic inflammation, or not or whether the subject is suffering from SIRS, or not or whether the subject is suffering from sepsis, or not or whether the subject is suffering from septic shock, or not.

[0052] Consequently, the labeled training patient data may be obtained by using data from a plurality of subjects, such as by using data from one or more clinical studies. As an example, data from at least 100 subjects, specifically data from at least 500 subjects or more, may be used for generating the labeled training patient data. For, each patient, firstly, abundance data for the biomarkers referred to herein may be generated. Further, for each subject, information on the systemic inflammation status may be obtained. Furthermore, additional information on the respective subject may be comprised in the labeling, such as information on the age of the subject, information on the gender, medical history information on the subject or the like. The aggregate of the labeled training data set of the subjects may then form or form part of the labeled training patient data. The labeled training data may also be obtained by using data from one or more medical studies. Thus, as will be shown, various medical studies have been performed, indicating the gene expression data of the patients and also indicating the respective known systemic inflammatory states of the patients. Therein, training data from more than one medical study may be combined.

[0053] Suitable regression analysis models may be selected from the group consisting of trained support vector machine (SVM) model, decision trees, logistic regression, random forests (RF), and Extreme Gradient Boosting (XGBoost). More specifically, said regression analysis model is a trained support vector machine (SVM) model in accordance with the present invention.

[0054] Advantageously, it was shown in the studies underlying the present invention that the biomarker panels (groups of biomarkers) described in this specification allow for reliably diagnosing systemic inflammation and allowing for differentiating between different conditions of systemic inflammation which may exhibit otherwise rather similar symptoms, i.e. SIRS, sepsis and septic shock. It has been found in the studies underlying the present invention that different panels of biomarkers aid diagnosis and, in particular, differential diagnosis of systemic inflammation. A first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6 or a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1 or a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3 may be determined for assessing systemic inflammation. It has been found further that the first group of biomarkers is particularly well suited to differentiate between SIRS, sepsis and septic shock in subjects to be investigated regardless of their age, while the second group of biomarkers is superior in adult subjects and the third group of biomarkers is superior in juvenile subjects. Moreover, as shown in the accompanying Examples below, determining the group of biomarkers consisting of ten biomarkers as described herein above has a superior diagnostic performance when compared to the diagnostic performance of single biomarkers or groups consisting of less biomarker (e.g., five biomarkers). However the diagnostic performance of groups with more than ten biomarkers, typically, does not increase the diagnostic performance in a significant manner. Thus, the aforementioned groups are well balanced between number of biomarkers and diagnostic performance.

[0055] Thanks to the present invention systemic inflammation can be reliably diagnosed and different systemic inflammation conditions such as SIRS, sepsis and septic shock can be differentiated from each other. In particular, patients showing severe symptoms in an ambulant or stationary set up such as in an emergency unit of a hospital can be reliably and fast diagnosed to suffer from any of the aforementioned systemic inflammation conditions and appropriate care measures can be applied.

[0056] All explanations and definitions of the terms made above apply mutatis mutandis for the following embodiments.

[0057] The present invention, in general, relates to the use of the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, AC0T4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3 in a sample of a subject exhibiting symptoms of systemic inflammation for assessing systemic inflammation. Typically, the term “use of the amounts of biomarkers from a group of biomarkers” refers to the use of the amounts of each of the biomarkers in the group of biomarkers, e.g. the amounts of at least ten biomarkers.

[0058] Preferably, said assessing systemic inflammation comprises identifying whether the subject suffers from SIRS, sepsis or septic shock.

[0059] The present invention also contemplates a device for assessing systemic inflammation comprising: a) an analyzer comprising detection agents capable of determining in a sample of a subject exhibiting symptoms of systemic inflammation the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3; b) an evaluation unit comprising a processor which is configured for comparing said determined amounts of biomarkers from said group of biomarkers to a stored reference and generating an assessment of systemic inflammation in the subject and a storage device providing the stored reference to the processor.

[0060] The term “device” as used herein refers to a system comprising the aforementioned analyzer and evaluation unit operatively linked to each other as to allow the determination of the presence, absence or abundance of biomarkers and evaluation thereof according to the method of the invention such that an assessment can be provided.

[0061] The analyzer, typically, comprises at least one detection element being capable of detecting the biomarkers present in the sample. Prior to introducing the sample into the detection element, the sample may be pre-treated by detection agent in order to generate detectable signals, e.g., by allowing the formation of biomarker-antibody complexes whereby the antibody as detection molecule comprises a detectable label that can be detected by the detection element. The detection element may also comprise a reaction zone that allows carrying out a chemical detection reaction such as a PCR. The detection element shall be adapted to determine the amount of the biomarkers. The determined amount can be subsequently transmitted to the evaluation unit. Preferably, said detection agents are antibodies that specifically bind to the biomarker proteins or nucleic acid molecules that specifically bind to biomarker RNA.

[0062] The evaluation unit comprises a processor, such as a computer, which is configured for comparing said determined amounts of biomarkers from said group of biomarkers to a stored reference and generating an assessment of systemic inflammation in the subject and a storage device providing the stored reference to the processor. The processor as referred to in accordance with the method of the present invention, typically, comprises a Central Processing Unit (CPU) and / or one or more Graphics Processing Units (GPUs) and / or one or more Application Specific Integrated Circuits (ASICs) and / or one or more Tensor Processing Units (TPUs) and / or one or more field-programmable gate arrays (FPGAs) or the like. The evaluation unit shall further comprise a storage device providing the stored reference to the processor. The evaluation unit, thus, may be a general purpose computer or a portable computing device, for example. It should also be understood that multiple computing devices may be used together, such as over a network or other methods of transferring data, for performing one or more steps of the methods disclosed herein. Exemplary computing devices include desktop computers, laptop computers, personal data assistants (“PDA”), cellular devices, smart or mobile devices, tablet computers, servers, and the like. In general, a data processing element comprises a processor capable of executing a plurality of instructions (such as a program of software). The processor shall have access to the storage device, such as a memory. A memory is a computer readable medium and may comprise a single storage device or multiple storage devices, located either locally with the computing device or accessible to the computing device across a network, for example. Computer-readable media may be any available media that can be accessed by the computing device and includes both volatile and non-volatile media. Further, computer readable-media may be one or both of removable and non-removable media. By way of example, and not limitation, computer- readable media may comprise computer storage media. Exemplary computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or any other memory technology, CD-ROM, Digital Versatile Disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used for storing a plurality of instructions capable of being accessed by the computing device and executed by the processor of the computing device. The evaluation unit may also comprise or has access to an output device. Exemplary output devices include fax machines, displays, printers, and files, for example. According to some embodiments of the present disclosure, a computing device may perform one or more steps of a method disclosed herein, and thereafter provide an output, via an output device, relating to a result, indication, ratio or other factor of the method. Preferably, said device is specifically adopted to carry out the method of the present invention.

[0063] Furthermore, the present invention relates to a kit for assessing systemic inflammation in a subject exhibiting symptoms thereof comprising detection agents capable of determining in a sample of said subject the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, AC0T4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3.

[0064] The term “kit” as used herein refers to collection of the aforementioned components, typically, provided separately or within a single container. The container also typically comprises instructions for carrying out the method of the present invention. These instructions may be in the form of a manual or may be provided by a computer program code which is capable of carrying out or supports the determination of the biomarkers referred to in the methods of the present invention when implemented on a computer or a data processing device. The computer program code may be provided on a data storage medium or device such as an optical storage medium (e.g., a Compact Disc) or directly on a computer or data processing device or may be provided in a download format such as a link to an accessible server or cloud.

[0065] Preferably, said detection agents comprised by the kit of the invention are antibodies that specifically bind to the biomarker proteins or nucleic acid molecules that specifically bind to biomarker RNA.

[0066] Moreover, the kit may usually comprise reference and / or calibration amounts for the biomarkers as described elsewhere herein in detail. The kit according to the present invention may also comprise further components which are necessary for carrying out the method of the invention such as solvents, buffers, washing solutions and / or reagents required for detection. Further, it may comprise the device of the invention either in parts or in its entirety.

[0067] Moreover, the invention relates to a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6, a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1, or a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3 for use in a method of diagnosing systemic inflammation.

[0068] The term “diagnosing” as used herein refers to the assessment of the health condition of a subject. Accordingly, diagnosing as used herein means assessing whether a subject suffers from a systemic inflammation. Preferably, the systemic inflammation is SIRS, sepsis or septic shock. Diagnosing as used herein refers also to the differentiation between different stages of systemic inflammation, i.e. SIRS, sepsis and septic shock.

[0069] As will be understood by those skilled in the art, such a diagnosing, although preferred to be, may usually not be correct for 100% of the investigated subjects. The term, however, requires that a statistically significant portion of subjects can be correctly diagnosed. Whether a portion is statistically significant can be determined without further ado by the person skilled in the art using various well known statistic evaluation tools as described elsewhere in the description.

[0070] The following are particular preferred embodiments in accordance with the present invention:

[0071] Embodiment 1 : A method for assessing systemic inflammation in a subject exhibiting symptoms thereof comprising: a) determining in a sample of said subject the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, AC0T4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3; b) comparing said determined amounts of biomarkers from said group of biomarkers to a reference; and c) assessing systemic inflammation in the subject.

[0072] Embodiment 2: The method of embodiment 1, wherein said amounts of biomarkers from the second group of biomarkers are determined and wherein said subject is an adult subject.

[0073] Embodiment 3: The method of embodiment 1, wherein said amounts of biomarkers from the third group of biomarkers are determined and wherein said subject is a juvenile subject.

[0074] Embodiment 4: The method of any one of embodiments 1 to 3, wherein said assessing systemic inflammation comprises identifying whether the subject suffers from SIRS, sepsis or septic shock.

[0075] Embodiment 5: The method of embodiment 4, wherein the reference is derived from one or more subject(s) known to suffer from SIRS and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from SIRS whereas amounts that differ from the reference are indicative for a subject not suffering from SIRS.

[0076] Embodiment 6: The embodiment of claim 4, wherein the reference is derived from one or more subject(s) known not to suffer from SIRS and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from SIRS.

[0077] Embodiment 7: The method of embodiment 4, wherein the reference is derived from one or more subject(s) known to suffer from sepsis and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from sepsis whereas amounts that differ from the reference are indicative for a subject not suffering from sepsis.

[0078] Embodiment 8: The method of embodiment 4, wherein the reference is derived from one or more subject(s) known not to suffer from sepsis and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from sepsis. Embodiment 9: The method of embodiment 4, wherein the reference is derived from one or more subject(s) known to suffer from septic shock and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from septic shock whereas amounts that differ from the reference are indicative for a subject not suffering from septic shock.

[0079] Embodiment 10: The method of embodiment 4, wherein the reference is derived from one or more subject(s) known not to suffer from septic shock and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from septic shock.

[0080] Embodiment 11 : The method of any one of embodiments 1 to 4, wherein said method comprises applying a regression analysis model for assessing systemic inflammation.

[0081] Embodiment 12: The method of embodiment 11, wherein said regression analysis model is a trained support vector machine (SVM) model.

[0082] Embodiment 13 : The method of any one of embodiments 1 to 12, wherein the protein amount or RNA amount of the biomarkers is determined.

[0083] Embodiment 14: The method of any one of embodiments 1 to 13, wherein said sample is a body fluid sample.

[0084] Embodiment 15: The method of embodiment 14, wherein said body fluid sample is a blood sample.

[0085] Embodiment 16: The method of embodiment 14 or 15, wherein said body fluid sample comprises leucocytes, preferably, peripheral blood mononuclear cells (PBMC).

[0086] Embodiment 17: The method of any one of embodiments 1 to 16, wherein said subject is a human.

[0087] Embodiment 18: The method of any one of embodiments 1 to 17, wherein said systemic inflammation is SIRS, sepsis or septic shock. Embodiment 19: The method of any one of embodiments 1 to 18, wherein said symptoms for systemic inflammation are selected from the group consisting of: hyperthermia or hypothermia, tachycardia, tachypnoea, leucocyte abnormalities, and organ failure.

[0088] Embodiment 20: Use of the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3; in a sample of a subject exhibiting symptoms of systemic inflammation for assessing systemic inflammation.

[0089] Embodiment 21 : The use of embodiment 20, wherein said assessing systemic inflammation comprises identifying whether the subject suffers from SIRS, sepsis or septic shock.

[0090] Embodiment 22: A device for assessing systemic inflammation comprising: a) an analyzer comprising detection agents capable of determining in a sample of a subject exhibiting symptoms of systemic inflammation the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3; b) an evaluation unit comprising a processor which is configured for comparing said determined amounts of biomarkers from said group of biomarkers to a stored reference and generating an assessment of systemic inflammation in the subject and a storage device providing the stored reference to the processor.

[0091] Embodiment 23: The device of embodiment 22, wherein said detection agents are antibodies that specifically bind to the biomarker proteins or nucleic acid molecules that specifically bind to biomarker RNA. Embodiment 24: A kit for assessing systemic inflammation in a subject exhibiting symptoms thereof comprising detection agents capable of determining in a sample of said subject the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3.

[0092] Embodiment 25: The kit of embodiment 24, wherein said detection agents are antibodies that specifically bind to the biomarker proteins or nucleic acid molecules that specifically bind to biomarker RNA.

[0093] Embodiment 26: The kit of embodiment 24 or 25, further comprising reference and / or calibration amounts for the biomarkers.

[0094] Embodiment 27: A first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6, a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1, or a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3 for use in a method of diagnosing systemic inflammation in a subject.

[0095] Embodiment 28: The first, the second, and / or the third group of biomarkers according to embodiment 27 for use in a method of diagnosing SIRS, sepsis and / or septic shock.

[0096] All references cited throughout this specification are herewith incorporated by reference with respect to the specifically mentioned disclosure content as well as in their entireties.

[0097] FIGURES Figure 1 shows a flow chart of an embodiment of a computer-implemented training method and of an embodiment of a computer-implemented classification method.

[0098] Figure 2 shows a flow chart of an embodiment of a computer-implemented training method.

[0099] Figure 3 shows a diagram of a performance of different trainable models.

[0100] Figure 4 shows a flow chart of machine learning experiments.

[0101] Figure 5 shows different accuracy metrics for different machine learning experiments with a trainable SVM model.

[0102] Figures 6A to 6C show the confusion matrices for the machine learning experiments.

[0103] Figures 7A and 7B show different accuracy metrics for different experiments with a trainable XGBoost model (Figure 7A) and a trainable SVM model (Figure 7B).

[0104] EXAMPLES

[0105] The Examples merely illustrate the invention. They shall not be construed as limiting the scope.

[0106] Example 1: Identifying biomarker panels using a computer-implemented classification method

[0107] Figure 1 shows a flow chart of an exemplary embodiment of a computer-implemented training method (denoted by reference number 110) and of an exemplary embodiment of a computer-implemented classification method (denoted by reference number 112). The computer- implemented training method 110 is a computer-implemented method of training at least one trainable model. The trainable model is configured for classifying a patient’s health condition into a systemic inflammatory state, specifically an inflammatory response state, the systemic inflammatory state being selected from a predetermined group of at least three systemic inflammatory states. The group of predetermined systemic inflammatory states may comprise or may consist of: the patient suffering from SIRS; the patient suffering from sepsis; the patient suffering from a septic shock. Additionally, one or more additional states may be comprised by the predetermined group of the at least three systemic inflammatory states. Thus, as an example and as outlined above, the predetermined group of the at least three systemic inflammatory states, besides the systemic inflammatory states “the patient suffering from SIRS”, “the patient suffering from sepsis”, and “the patient suffering from a septic shock”, may, additionally, contain the state “the patient being in an apparently healthy state”, or, equivalently, “the patient apparently not suffering from any of SIRS, sepsis and septic shock”, notwithstanding the fact that the patient may suffer from other diseases.

[0108] The training method 110 and / or the classification method 112 comprises the following method steps, which, as an example, may be performed in the given order. However, a different order is also feasible. Further, it is possible to perform two or more of the method steps simultaneously or in a fashion overlapping in time. Further, it is also possible to perform one, more than one or even all of the method steps repeatedly.

[0109] The training method 110 comprises the following steps: a. (denoted by reference number 114) providing the trainable model; b. (denoted by reference number 116) retrieving labeled training patient data, the training patient data comprising gene expression data of patients having known systemic inflammatory states; and c. (denoted by reference number 118) training the trainable model on the labeled training patient data.

[0110] One or more than one trainable model may be used. Even though the method generally relates to trainable models suited for classifying the patient’s health condition, e.g. trainable models listed above, the trainable model specifically may be or may comprise at least one trainable SVM model and / or at least one trainable XGBoost model. These models, for the present application, out of the available trainable model is in standard software libraries, have shown to provide excellent classification results for classifying a patient’s health condition according to systemic inflammatory states. Examples of a trainable SVM model and a trainable XGBoost model are given in the following Figures.

[0111] The labeled training patient data may be obtained by using data from a plurality of patients, such as by using data from one or more clinical studies. As an example, data from at least 100 patients, specifically data from at least 500 patients or more, may be used for generating the labeled training patient data. For, each patient, firstly, gene expression data may be gen- erated. Further, for each patient, information on the systemic inflammatory state of the respective patient may be obtained, such as the patient suffering from SIRS, the patient suffering from sepsis, the patient suffering from a septic shock. Additionally, the following state may also be comprised: the patient being in an apparently healthy state. As outlined above, diagnostic indicators may be used other than gene expression data for obtaining the systemic inflammatory state of the respective patient, such as by detecting the presence or absence of the characteristic symptoms for each of the systemic inflammatory states. Then, for each patient, the gene expression data are labeled at least with the respective information on the systemic inflammatory state of the respective patient, in order to obtain a labeled training data set for the respective patient. In addition, and optionally, additional information on the respective patient may be comprised in the labeling, such as information on the age of the patient, information on the gender of the patient, medical information on the patient and the like. The aggregate of the labeled training data set of the patients may then form part of the labeled training patient data.

[0112] The gene expression data of the labeled training patient data in step b., specifically may be derived from peripheral blood mononuclear cells (PBMC) and are, preferably, obtained by mRNA analysis.

[0113] The training method 110 specifically may comprise splitting the labeled training patient data into a training data set and a test data set. Thus, more specifically, the splitting into a training data set and a test data set may comprise a x%-y% splitting of the labeled training patient data, with x% being in the range 60 to 90, specifically in the range 65 to 75, and more specifically x%= 70, and with y%=100-x. Therein, x% denotes the training data set and y% denotes the test data set.

[0114] The training method 110 may further compromise a cross-validation in the training data set. Thus, the data of the training data set may be further split into k subsets or folds of equal size, with & being at least 2 or more folds, specifically in the range 3 to 10, more specifically k=5. The training and validation may be repeated k times, and each time the data of a different subset or fold may be used for validation. Additionally or alternatively, the training method may further comprise repeating the splitting of the labeled training data into training data set and test data set one or more times, specifically for a number of times in the range 10 to 40 times, more specifically 20 times. Thus, a validation of the model may be performed with an xi%-yi% splitting of the labeled training patient data, and at least one additional X2%-y2% splitting of the labeled training patient data, with xi and x2describing different partitions of the labeled training patient data, wherein, specifically, xi%=X2%. As an example, a degree of discrepancy between the results obtained for the multiple iterations may be used for qualifying and / or quantifying the training result.

[0115] As shown in Figure 1, the training method 110 specifically may comprise splitting the labeled training patient data into a training data set and a test data set. The training method may, then, further comprises the following step: d. (denoted by reference number 120) at least one validation step, the validation step comprising testing the accuracy of the training by using the test data set.

[0116] The testing of the accuracy specifically may comprise using at least one model accuracy metrics. Various model accuracy metrics are generally known in the field of machine learning. Specifically, one or more or even all of the following model accuracy metrics may be used: overall accuracy, balanced accuracy, weighted fl score. Other options, however, are also feasible.

[0117] Further, in the exemplary embodiment of Figure 1, the training method 110 may comprise the following step: e. (denoted by reference number 122) determining at least one target set of relevant genes, by using at least one feature extraction method.

[0118] Various feature extraction methods are generally known to the skilled person in the field of machine learning. As an example, the feature extraction method may comprise considering a permutation feature importance. Additionally or alternatively, the importance of the features may be quantified, such as by quantifying the influence a variation of the value of the respective feature has on the accuracy of the model. The feature extraction method may then, as an example, also comprise considering a feature importance hierarchy. Thus, as an example, the feature extraction method may comprise selecting all features having a feature importance of at least one threshold value. Additionally or alternatively, the features may be ordered according to their feature importance, followed by selecting the most important features such that these selected features, in combination, result in a model accuracy metrics of at least one accuracy threshold value. Additionally or alternatively, the feature extraction method may comprise selecting a predetermined number of features highest in ranking with respect to their feature importance. Thus, as an example, the feature extraction method may also comprise, additionally or alternatively, selecting a group of genes of the gene expression data of the patients with the highest ranking in the feature importance hierarchy to be the target set of relevant genes, specifically for each age group of patients separately, more specifically at least one of selecting a predetermined number of genes of the gene expression data of the patients with the highest ranking in the feature importance hierarchy to be the target set of relevant genes; selecting the genes of the gene expression data of the patients having a feature importance of at least one threshold value to be the target set of relevant genes; ordering the genes according to their feature importance, followed by selecting the most important genes which, in combination, result in a model accuracy according to a model accuracy metrics of the trained model of at least one accuracy threshold value to be target set of relevant genes; ordering the genes according to their feature importance, followed by selecting the most important genes to be target set of relevant genes, until adding a further gene results in a gain in a model accuracy of the trained model according to a model accuracy metrics which is below a gain threshold. Again, additionally or alternatively, the feature extraction method may also comprise selecting a predetermined number of genes of the gene expression data of the patients with the highest ranking in the feature importance hierarchy to be the target set of relevant genes. For example, the feature extraction method may comprise ordering the genes according to their feature importance, specifically according to their feature importance with respect to a model accuracy according to a model accuracy metrics of the trained model. Genes having a high feature importance may be ordered above genes having a low feature importance. The group of the most important genes may then be selected such that the group of the most important genes may result in a model accuracy above at least one accuracy threshold value to be achieved. The group of the most important genes may be selected to be the target set of relevant genes. Alternatively or additionally, the ordered genes may be selected in an order beginning with a most important feature followed by selecting the second most important feature and so on. The most important genes may be selected to be the target set of relevant genes such that all of the most important features are selected until adding a further gene results in a gain in a model accuracy of the trained model according to a model accuracy metrics which is below a gain threshold. The further gene may not form part of the selected most important genes. Other means and methods of feature extraction, from the training results, may also be used in addition or as an alternative.

[0119] The feature extraction method may be performed such that a reasonable number of genes of the gene expression data of the patients are selected to be the target set of relevant genes. As an example, for practical applications, selecting a predetermined number of 3 to 20 genes is generally suitable for diagnostic handling, specifically a predetermined number of 5 tol5 genes, more specifically 10 genes. Further, as outlined above, Figure 1 shows an exemplary embodiment of the computer-implemented classification method 112 of classifying a patient’s health condition into a systemic inflammatory state, specifically an inflammatory response state. The systemic inflammatory state is selected from a predetermined group of at least three systemic inflammatory states, specifically, in this example, comprising the systemic inflammatory states as described above.

[0120] The classification method 112 comprises the following steps: i. (denoted by reference number 124) retrieving at least one trained model; ii. (denoted by reference number 126) retrieving patient data of the patient, the patient data comprising gene expression data of the patient, the gene expression data comprising at least one predetermined target set of relevant genes; and iii. (denoted by reference number 128) applying the trained model to the target set of relevant genes of the patient data, thereby assigning a systemic inflammatory state to the patient.

[0121] Specifically, in the example of Figure 1, the trained model being retrieved in step i. of the classification method 112 may be the trainable model being trained by using the training method 110 as described above. However, in principle, in other embodiments of the classification method 112, the trained model may be retrieved independent from the training method 110.

[0122] Further, as shown in Figure 1, the classification method 112 may comprise the following step: iv. (denoted by reference number 130) outputting the assigned systemic inflammatory state obtained in step iii.

[0123] The output, as an example, may take place in one or more of the following fashions: by electronic output, by data transfer, by data storage, by displaying, by acoustic output, by haptic output, by printing a report or by a combination of one or more or even all of the before-mentioned options. Thus, as an example, the assigned systemic inflammatory state may be displayed on a computer display.

[0124] Additionally, as can be seen in Figure 1, the classification method 112 may further comprise the following step: v. (denoted by reference number 132) providing at least one proposal for a therapeutic measure in accordance with the assigned systemic inflammatory state obtained in step iii.

[0125] The providing of the at least one proposal specifically may take place in one or more of the following fashions: by electronic output, by data transfer, by data storage, by displaying, by acoustic output, by haptic output, by printing a report or by a combination of one or more or even all of the before-mentioned options. Thus, as an example, the proposal may be displayed on a computer display. The method may imply using at least one transformation and / or algorithm for generating the at least one proposal depending on the assigned systemic inflammatory state. Thus, as an example, the method may imply using a lookup table having listed therein, one or more therapeutic measures for each systemic inflammatory state, such as one or more recommended therapeutic measures from textbooks.

[0126] Further details and possible embodiments of the training method 110 and / or the classification method 112 will be discussed with regard to the following Figures. Thus, for details and / or possible embodiments of the training method 110 and / or the classification method 112, reference is made to the description of the following Figures.

[0127] In Figures 2 to 6C, a further example of the present invention is shown. Therein, Figure 2 shows a flow chart of a further embodiment of the computer-implemented training method 110. In this example, the training method 110 may provide a machine learning algorithm based on gene expression data of patients from different public studies, such as from different microarrays, to classify systemic inflammatory states, e.g. sepsis conditions, specifically the systemic inflammatory states described above, e.g. “the patient suffering from SIRS”, “the patient suffering from sepsis”, and “the patient suffering from a septic shock”, and, in particular, to find relevant biomarkers. Further, different training methods 110 were performed for different age groups, such as pediatric, adults, as will be outlined in further details below.

[0128] The training method 110, in this example, comprises providing the trainable model (step a., denoted by reference number 114) and retrieving labeled training patient data (step b., denoted by reference number 116). Further, the training method 110 may comprise, after performing steps a. and b., at least one hyperparameter tuning step for tuning hyperparameters of the trainable model (denoted by reference number 133). The hyperparameter tuning step 133, as shown in Figure 2, may be performed at least once before performing step c. It is, however, also possible to implement a plurality of tuning steps, intermitting with one or more partial training steps, e.g. in order to improve or even optimize the tuning of the hyperparameters during the process.

[0129] The training method 110 may then proceed with training the trainable model in step c. (denoted by reference number 118), which is denoted in the following also as “machine learning experiment”, the at least one validation step (denoted by reference number 120), and the determining of the at least one target set of relevant genes, by using the at least one feature extraction method (denoted by reference number 122). In this example, the feature extraction method may specifically comprise considering a permutation feature importance, as will be outlined in further detail below.

[0130] In the example shown in Figures 2 to 6C, labeled patient data of 1024 patients from 27 individual studies were used. The gene expression data of the labeled training patient data in step b., specifically may be derived from peripheral blood mononuclear cells (PBMC) and are, preferably, obtained by mRNA analysis. The gene expression data in this example comprised 17808 different genes derived from PBMC. The patient data were obtained via the following GEO accession codes / study codes:

[0131] GEO accession codes / study codes and download links:

[0132] GSE8121 : https: / / www.ncbi.nlm.nih.gov / geo / query / acc.cgi?acc=GSE8121

[0133] GSE9692: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE9692

[0134] GSE11755: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSEl 1755 GSE13904: https: / / www.ncbi.nlm.nih.gov / geo / query / acc.cgi?acc=GSE13904 GSE57065: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE57065 GSE66099: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE66099 GSE26378: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE26378 GSE26440: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE26440

[0135] GSE27131 : https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE27131 GSE22098: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE22098 GSE63042: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE63042 GSE95233: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE95233 GSE9960: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE9960

[0136] GSE28750: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE28750 GSE131411 : https: / / www.ncbi.nlm.nih.gov / geo / query / acc.cgi?acc=GSE131411 GSE110487: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSEl 10487 E-MTAB-1548: https: / / www.ebi.ac.uk / biostudies / arrayexpress / studies / E-MTAB-1548 GSE74224: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE74224 E-MTAB-4421 : https: / / www.ebi.ac.uk / biostudies / arrayexpress / studies / E-MTAB- 4421 ?query=E-MT AB-4421

[0137] SCP548: https: / / singlecell.broadinstitute.org / single_cell / study / SCP548 / an-immune-cell- signature-of-bacterial-sepsis-patient-pbmcs

[0138] GSE25504: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE25504 GSE54514: https: / / www.ncbi.nlm.nih.gov / geo / query / acc.cgi?acc=GSE54514 GSE69528: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE69528 GSE119217: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSEl 19217 GSE157103: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSEl 57103 GSE154998: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSEl 54998 GSE149689: https: / / www.ncbi. nlm.nih.gov / geo / query / acc.cgi?acc=GSE149689

[0139] Further, in the example shown in Figures 2 to 6C, a pre-study was performed comparing different trainable models, such as a decision tree model (denoted by reference number 134), a Random Forest model (denoted by reference number 136), a light GBM classifier (denoted by reference number 138), a KNeighbors Classifier (denoted by reference number 140), a Support Vector Machine (SVM) model (denoted by reference number 142), a GaussianNB() model (denoted by reference number 144) and a LogisticRegression model (denoted by reference number 146). The results of this pre-study are shown in Figure 3. Specifically, Figure 3 shows a diagram with the performance different trainable models. The performance of the trainable models were evaluated using the balanced accuracy (denoted by reference number 145) and the overall accuracy (denoted by reference number 147). For the pre-study, the labeled patient data were split into 70% training data and 30% testing data. The training data were used to find the best model parameters using a 5-fold cross validation. The training data set and the testing data set were normalized. The splitting into 70% training data and 30% testing data was repeated 20 times, specifically with each split having the 5-fold cross- validation in each set of training data. The pre-study, as can be seen in Figure 3, showed that the SVM model performs better than the other tested trainable models. Thus, for the machine learning experiments of Figures 4 to 6C, the SVM model was selected for the trainable model. The trainable SVM model was trained using the following hyperparameters:

[0140] Regularization parameter: C: 1.0;

[0141] Kernel: linear;

[0142] Penalty function: LI (Lasso); Loss Function: squared hinge.

[0143] In this example, several machine learning experiments were defined according to Table 1 :

[0144] Table 1 : Overview on the machine learning experiment and studies.

[0145] A flow chart of the machine learning experiments is shown in Figure 4. For the machine learning experiments, a naive approach was used. The machine learning experiments, i.e. the training in step c. of the training method 110, may provide the best trained SVM model for each use case, e.g. for all data or stratified by age group, based on the normalized patient data. Prior to the machine learning experiment, as shown in Figure 2, the hyperparameter tuning step 133, e.g. a grid search, may be performed to identify the best model parameters for the linear SVM using cross-validation.

[0146] Further, the machine learning experiment of the example shown in Figures 2 to 6C comprised splitting the labeled training patient data into the training data set and the test data set (denoted by reference number 148). In this example, the splitting comprised splitting the labeled training patient data into 70% of training data and 30% of test data. Further, a hyperparameter tuning step was used (denoted by reference number 150).

[0147] As shown in Figure 4, the machine learning experiment further comprised training and testing the trainable SVM model (denoted by reference number 152). In a training and testing step, generally, several model accuracy metrics may be computed. For example, one or more of the overall accuracy, balanced accuracy, and weighted fl score may be computed. Finally, after the training and testing step 152, the machine learning experiment of the example shown in Figures 2 to 6C comprised determining of the at least one target set of relevant genes, by using the at least one feature extraction method (denoted by reference number 122), which, in the example shown in Figures 2 to 6C, specifically comprised considering a permutation feature importance, as will be outlined in further detail below. Each of these steps may be performed repeatedly, specifically, in this example, for a number of 20 times (denoted by reference number 153). The results of the machine learning experiments are shown in Figures 5 to 6C. Specifically, Figure 5 shows different accuracy metrics for different experiments with the trainable SVM model. Figure 5 shows the overall accuracy 154, the balanced accuracy 156, and the weighted fl score 158 for the different machine learning experiments performed in this example. Specifically, Figure 5 shows these model accuracy metrics for the experiments “PEDIATRIC” (denoted by reference number 160), “ALL STUDIES” (denoted by reference number 164) and “ADULT” (denoted by reference number 166). As can be seen in Figure 5, the trained SVM model achieves accuracy scores of 0.8 or higher, except for the balanced accuracy of the PEDIATRIC experiment.

[0148] Figures 6A to 6C show the confusion matrices for the machine learning experiments of Figure 4. Specifically, , Figure 6A shows the confusion matrix for the machine learning experiment “ALL STUDIES”, Figure 6B shows the confusion matrix for the machine learning experiment “ADULT” and Figure 6C shows the confusion matrix for the machine learning experiment “PEDIATRIC”. In the Figures 6 A to 6C, the rows of the confusion matrices represent the true systemic inflammatory states “the patient suffering from sepsis” (denoted by reference number 168), “the patient suffering from SIRS” (denoted by reference number 170), and “the patient suffering from a septic shock” (denoted by reference number 172), wherein the columns represent the predicted systemic inflammatory states. As can be seen in Figures 6A to 6C, the confusion matrices are normalized confusion matrices, thus, representing the respective relative frequency.

[0149] Further, in the example shown in Figures 2 to 6C, as outlined above, the determining of the at least one target set of relevant genes, by using the at least one feature extraction method comprised considering a permutation feature importance. The permutation feature importance provided the most relevant genes. As outlined above, the splitting was repeated 20 times and, thus, weights of each gene were summed and ranked accordingly. In order to identify the most relevant genes, permutation feature importance was performed for each machine learning experiment. The permutation feature importance generally may comprise a decrease in a model score when a single gene value is randomly shuffled. This shuffle may break the relationship between the gene and the target and, thus, the decrease in the model score may be indicative of how much the model depends on the gene. The permutation feature importance may benefit from being model agnostic and can be calculated many times with different permutations of the gene. For determining the permutation feature importance, all genes (PBMC) which are in common between the studies were considered as input features (n=17808).

[0150] For identifying the relevant genes, the following approach was used: The feature importance was determined based on permutation feature importance from each of the splittings. Specifically, the 70% training data and 30% testing data split was repeated for a number of 20 times, and the sum of weights for each splitting was computed for the full PBMC dataset, and the top ten highest genes in ranking were identified for each machine learning experiment.

[0151] The relevant genes, which then may be used as a target set of relevant genes in the classification method 112, for the example shown in Figures 2 to 6C, is shown in Table 2.

[0152] Table 2: The relevant genes determined by using the example shown in Figures 2 to 6C.

[0153] The training method 110, in this example, was performed using different trainable models as a starting point. Although Artificial Neural Networks were not tested, yet, in principle, they are also feasible for being used as the trainable model for the training method 110 and / or the classification method 112 according to the present invention. Further, the training method 110 in this example used a 5-fold cross validation approach by not considering a certain percentage of the labeled patient data for training in order to test the trainable model, wherein the splitting of the labeled patient data was repeated for a number of 20 times. Alternatively or additionally, a study wise validation may also be performed for testing the trainable model.

[0154] Figures 7A and 7B show further experiments comparing training results for a trainable XGBoost model with training results for a trainable SVM model. The experiments were performed on the basis of the training data used in Figures 2 to 6C above, so reference regarding the studies and the training data may be made to the description of these Figures. Therein, accuracy metrics for different experiments with training a trainable XGBoost model (Figure 7A) and training a trainable SVM model (Figure 7B) are shown. Specifically, Figures 7A and 7B show the overall accuracy 154, the balanced accuracy 156, and the weighted fl score 158 for the machine learning experiments “PEDIATRIC” (denoted by reference number 160), “ALL STUDIES” (denoted by reference number 164) and “ADULT” (denoted by reference number 166). As outlined above, the labeled patient data were the same used for the example of Figures 2 to 6C. However, in this second example, a trainable XGBoost model was used as the trainable model. The trainable XGBoost model was trained using the following hyperparameters: booster- gbtree', colsample_bytree= 1.0, gamma= 1, max_depth= 3, min_child_weight= 5, subsample= 0.6.

[0155] The results of Figures 7A and 7B are show in comparison in Table 3:

[0156] Table 3: Accuracy results for a training of a trainable SVM model and a trainable XGBoost model. These results show that, after training, the trained XGBoost model is basically as accurate for use as trained models in a classification method of classifying a patient’s health condition into a systemic inflammatory state as the SVM model, so both models may generally be used.

[0157] Example 2: Comparison of diagnostic performance within patients without regarding the age Based on the scoring made according to Example 1, the following top 20 discriminating biomarkers were identified:

[0158] Table 4: Top 20 discriminating biomarker

[0159] The diagnostic performance was compared between the top 20, top 10, top 5 and the single biomarkers of this group using the Fl score. The Fl score is a machine learning evaluation metric that measures the model performance. The combination of TOP 10 biomarkers was compared to single biomarker scores with higher accuracies.

[0160] Table 5: Diagnostic performance

[0161] Superior results were obtained for a group consisting of the following (top 10) biomarkers: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6.

[0162] The mRNA amount (abundance) of genes suitable as biomarkers in the investigated patient collectives was derived from the gene expression analyses referred to in Example 1, supra. Distribution (0.25, 0.5 and 0.75 quantiles) is shown in the following Table 6. Table 6: Distribution (quantiles) of the investigated patient collectives Example 3: Comparison of diagnostic performance within adult patients

[0163] Based on the scoring made according to Example 1, the following top 20 discriminating biomarkers were identified:

[0164] Table 7: Top 20 discriminating biomarker

[0165]

[0166] The diagnostic performance was compared between the top 20, top 10, top 5 and the single biomarkers of this group using the Fl score.

[0167] Table 8: Diagnostic performance

[0168] Superior results were obtained for a group consisting of the following (top 10) biomarkers: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1.

[0169] Distribution (quantiles) of the investigated patient collectives is shown in the following Table 9. Table 9: Distribution (quantiles) of the investigated patient collectives

[0170] Example 4: Comparison of diagnostic performance within juvenile (pediatric) patients Based on the scoring made according to Example 1, the following top 20 discriminating biomarkers were identified:

[0171] Table 10: Top 20 discriminating biomarker

[0172] The diagnostic performance was compared between the top 20, top 10, top 5 and the single biomarkers of this group using the Fl score.

[0173] Table 11 : Diagnostic performance

[0174] Superior results were obtained for a group consisting of the following (top 10) biomarkers: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3.

[0175] Distribution (quantiles) of the investigated patient collectives is shown in the following Table 12.

[0176] Table 12: Distribution (quantiles) of the investigated patient collectives

[0177] Example 5: Determination of biomarkers in samples a) Determination of protein biomarkers

[0178] A whole blood, plasma or serum of a patient suspected to suffer from SIRS, sepsis or septic shock will be pretreated for protein analysis. The pretreated sample will be analyzed using antibodies that specifically bind to the biomarkers of the first, second or third group referred to in Examples 2 to 4. Specific binding of a biomarker will be determined by using, e.g., a sandwich assay format. In said assay format, the biomarkers will be immobilized on a solid support using a capture antibody specifically binding to the biomarker. After washing, the bound biomarker immobilized by the capture antibody will be determined by using a detection antibody specifically binding to the biomarker when captured by the capture antibody. The specifically bound detection antibody will be subsequently detected using a detectable label such as fluorescent label, an enzymatic label or the like. b) Determination of mRNA biomarkers

[0179] A whole blood, plasma or serum of a patient suspected to suffer from SIRS, sepsis or septic shock will be pretreated for mRNA analysis. The pretreated sample will be analyzed using quantitative RT-PCR specifically determine the biomarkers of the first, second or third group referred to in Examples 2 to 4. The total mRNA in the sample will be reverse transcribed in order to obtain cDNA for PCR analysis. Specific fluorescent-labeled primers for amplifying biomarker cDNA will be used for quantitative PCR.

[0180] List of reference numbers training method classification method providing the trainable model retrieving labeled training patient data training the trainable model validation step determining a target set of relevant genes retrieving a trained model retrieving patient data of the patient applying the trained model to the target set of relevant genes outputting the assigned systemic inflammatory state providing at least one proposal hyperparameter tuning step decision tree model

[0181] Random Forest model light GBM classifier

[0182] KNeighbors Classifier

[0183] SVM model

[0184] GaussianNB() model balanced accuracy

[0185] LogisticRegression model overall accuracy splitting the labeled training patient data intermitting hyperparamter tuning step training and testing step repetitions overall accuracy balanced accuracy weighted fl score

[0186] PEDIATRIC

[0187] ALL STUDIES

[0188] ADULT the patient suffering from sepsis the patient suffering from SIRS 172 the patient suffering from a septic shock

Claims

Claims1. A method for assessing systemic inflammation in a subject exhibiting symptoms thereof comprising: a) determining in a sample of said subject the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3; b) comparing said determined amounts of biomarkers from said group of biomarkers to a reference; and c) assessing systemic inflammation in the subject.

2. The method of claim 1, wherein said amounts of biomarkers from the second group of biomarkers are determined and wherein said subject is an adult subject.

3. The method of claim 1, wherein said amounts of biomarkers from the third group of biomarkers are determined and wherein said subject is a juvenile subject.

4. The method of any one of claims 1 to 3, wherein said assessing systemic inflammation comprises identifying whether the subject suffers from SIRS, sepsis or septic shock.

5. The method of claim 4, wherein the reference is derived from one or more subject(s) known to suffer from SIRS and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from SIRS whereas amounts that differ from the reference are indicative for a subject not suffering from SIRS.

6. The method of claim 4, wherein the reference is derived from one or more subject(s) known not to suffer from SIRS and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from SIRS.

7. The method of claim 4, wherein the reference is derived from one or more subject(s) known to suffer from sepsis and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from sepsis whereas amounts that differ from the reference are indicative for a subject not suffering from sepsis.

8. The method of claim 4, wherein the reference is derived from one or more subject(s) known not to suffer from sepsis and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from sepsis.

9. The method of claim 4, wherein the reference is derived from one or more subject(s) known to suffer from septic shock and wherein amounts that are essentially identical to the reference are indicative for a subject suffering from septic shock whereas amounts that differ from the reference are indicative for a subject not suffering from septic shock.

10. The method of claim 4, wherein the reference is derived from one or more subject(s) known not to suffer from septic shock and wherein amounts that are essentially identical to the reference are indicative for a subject not suffering from septic shock.

11. The method of any one of claims 1 to 4, wherein said method comprises applying a regression analysis model for assessing systemic inflammation.

12. The method of any one of claims 1 to 11, wherein said systemic inflammation is SIRS, sepsis or septic shock.

13. Use of the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3in a sample of a subject exhibiting symptoms of systemic inflammation for assessing systemic inflammation.

14. A device for assessing systemic inflammation comprising: a) an analyzer comprising detection agents capable of determining in a sample of a subject exhibiting symptoms of systemic inflammation the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3; b) an evaluation unit comprising a processor which is configured for comparing said determined amounts of biomarkers from said group of biomarkers to a stored reference and generating an assessment of systemic inflammation in the subject and a storage device providing the stored reference to the processor.

15. A kit for assessing systemic inflammation in a subject exhibiting symptoms thereof comprising detection agents capable of determining in a sample of said subject the amounts of biomarkers from a group of biomarkers selected from i) a first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6; ii) a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1; or iii) a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3.

16. A first group of biomarkers comprising: POMK, NEK6, KCNA5, LARGE2, ZNF425, NACA2, CFAP57, SPINT1, ZNF492, and S100A6, a second group of biomarkers comprising: NEK6, SRPK3, TNFSF8, S100A6, NMUR1, DHFR, HIST1H4D, ZDHHC4, TRAF3, and SGMS1, or a third group of biomarkers comprising: C9orfl35, ZNF425, ACOT4, SPDYA, DAPP1, LY86, ZPBP2, RPL3L, UPK1B, and APBB3 for use in a method of diagnosing systemic inflammation in a subject.

Images