Method and system for assisting in diagnosing irritable bowel syndrome
View Patent ↗The present invention provides methods, systems, and code for accurately classifying or diagnosing a sample from an individual as an IBS sample. The methods and systems of the present invention are useful for ruling out one or more diseases or disorders that share a similar clinical presentation as IBS followed by identifying (i.e., ruling in) IBS using statistical algorithm(s) and/or empirical data. In particular, the methods and systems of the present invention use a first combination of learning statistical classifier systems to rule out IBD with an accuracy of greater than about 90% and a second combination of learning statistical classifier systems to rule in IBS in a non-IBD sample with an accuracy of greater than about 80%.
1. A method for classifying whether a sample from an individual not having inflammatory bowel disease (IBD) is associated with irritable bowel syndrome (IBS), the method comprising:
(a) measuring a concentration level of at least one marker in said sample, wherein said at least one marker comprises an anti-flagellin antibody; and
(b) applying a combination of at least two learning statistical classifier systems to the measured concentration level of said at least one marker to classify said sample as an IBS sample or as a non-IBS sample.
2. The method of claim 1 , wherein said at least one marker further comprises an anti-neutrophil cytoplasmic antibody (ANCA), an anti- Saccharomyces cerevisiae immunoglobulin A antibody (ASCA-IgA), an anti- Saccharomyces cerevisiae immunoglobulin G antibody (ASCA-IgG), an anti-outer membrane protein C (anti-OmpC) antibody, an anti-I2 antibody, a perinuclear anti-neutrophil cytoplasmic antibody (pANCA), or combinations thereof.
3. The method of claim 1 , wherein said sample is selected from the group consisting of serum, plasma, whole blood, and stool.
4. The method of claim 1 , wherein said combination of at least two learning statistical classifier systems comprises a decision/classification tree in combination with a neural network or support vector machine.
5. The method of claim 4 , wherein said decision/classification tree is a classification and regression tree (C&RT) or a random forest.
6. The method of claim 4 , wherein said combination of at least two learning statistical classifier systems is used in tandem.
7. The method of claim 6 , wherein said decision/classification tree is first used to generate a probability value based upon the level of said at least one marker.
8. The method of claim 7 , wherein said neural network or support vector machine is then used to classify IBS in said sample based upon said probability value and the level of said at least one marker.
9. The method of claim 1 , wherein said combination of at least two learning statistical classifier systems classifies said sample with a specificity of at least 80%.
10. The method of claim 1 , wherein said combination of at least two learning statistical classifier systems classifies said sample with an overall accuracy of at least 60%.
11. The method of claim 1 , wherein the concentration level of said at least one marker is measured by assaying said sample with an immunoassay.
12. The method of claim 11 , wherein said immunoassay is an enzyme-linked immunosorbent assay (ELISA).
13. The method of claim 1 , wherein the concentration level of anti-flagellin antibody is measured by assaying the binding between the anti-flagellin antibody and a flagellin protein or an immunoreactive fragment thereof.
14. The method of claim 13 , wherein said flagellin protein comprises Cbir-1 flagellin, flagellin X, flagellin A, flagellin B, immunoreactive fragments thereof, or combinations thereof.
15. The method of claim 1 , wherein said method further comprises sending the results from said classification to a clinician.
16. The method of claim 1 , wherein said method further provides a diagnosis in the form of a probability that said individual has IBS.
17. The method of claim 1 , wherein said IBS is characterized by at least one symptom selected from the group consisting of abdominal pain, abdominal discomfort, change in bowel pattern, loose or more frequent bowel movements, diarrhea, constipation, and a combination thereof.
18. The method of claim 1 , wherein said method further comprises administering to said individual a therapeutically effective amount of a drug useful for treating one or more symptoms associated with IBS if said sample is classified as an IBS sample.
19. The method of claim 18 , wherein said drug is selected from the group consisting of serotonergic agents, antidepressants, chloride channel activators, guanylate cyclase agonists, antibiotics, opioids, neurokinin antagonists, antispasmodic or anticholinergic agents, belladonna alkaloids, barbiturates, free bases thereof, pharmaceutically acceptable salts thereof, and combinations thereof.
20. The method of claim 1 , wherein said anti-flagellin antibody comprises an anti-Cbir-1 flagellin antibody.