Method of predicting development and severity of graft-versus-host disease

1. A method for assessing a risk of a patient receiving a transplant of pluripotent hematopoietic stem cells (PHSC) or bone marrow developing graft-versus-host disease or characterizing such disease, comprising the steps of:

(a) performing MALDI-TOF mass spectrometry on a blood-based sample obtained from the patient after the PHSC or bone marrow transplant by subjecting the sample to at least 100,000 laser shots and acquiring mass spectral data;

(b) obtaining integrated intensity values in the mass spectral data of a multitude of pre-determined mass-spectral features; and

(c) operating on the mass spectral data with a programmed computer implementing a classifier configured as a combination of filtered mini-classifiers using a regularized combination method,

wherein in the operating step the classifier compares the integrated intensity values with feature values of a training set of class-labeled mass spectral data obtained from a multitude of patients having received a transplant of PHSC or bone marrow with the values obtained in step (b) with a classification algorithm and generates a class label for the sample, wherein the class label is associated with the risk of a patient providing the sample developing graft-versus-host disease or characterizing the graft-versus-host disease.

2. The method of claim 1 , wherein the operating step is performed multiple times by different classifiers, each configured as a combination of filtered mini-classifiers using a regularized combination method and addressing a different clinical question associated with the development or characterization of graft-versus-host disease, and the method further comprising the step of generating a panel of class label results, one for each operating step.

3. The method of claim 2 , wherein one of the classifiers addresses the clinical question of whether the patient is likely to develop acute graft-versus host disease.

4. The method of claim 2 , wherein one of the classifiers addresses the clinical question of whether the patient is likely to develop acute graft-versus host disease at grade II or higher as compared to not developing acute-graft-versus-host disease or developing acute graft-versus-host disease only at grade 1 .

5. The method of claim 2 , wherein one of the classifiers addresses the clinical question of whether the patient is likely to develop chronic graft-versus-host disease after developing acute graft-versus-host disease.

6. The method of claim 1 , wherein the obtaining step (b) comprises obtaining integrated intensity values of at least 50 features listed in Appendix A.

7. The method of claim 6 , wherein the obtaining step comprises obtaining integrated intensity values of at least 100 features listed in Appendix A.

8. The method of claim 6 , wherein the obtaining step comprises obtaining integrated intensity values of at least 200 features listed in Appendix A.

9. A classifier for assessing a risk of a patient receiving a transplant of pluripotent hematopoietic stem cells (PHSC) or bone marrow developing graft-versus-host disease or characterizing such disease, comprising in combination:

a memory storing a reference set of mass spectral data obtained from blood-based samples from a multitude of patients having received a transplant of PHSC or bone marrow and an associated class label;

a programmed computer configured to implement a classifier configured as a combination of filtered mini-classifiers with drop-out regularization;

wherein the reference set of mass spectral data includes feature values of at least some of the m/z features listed in Appendix A.

10. The classifier of claim 9 , wherein the reference set of mass spectral data is obtained from each of the blood-based samples by applying at least 100,000 laser shots to the blood-based samples using MALDI-TOF mass spectrometry.

11. A laboratory testing system for conducting tests on blood-based samples from patients receiving pluripotent hematopoietic stem cells (PHSC) or bone marrow transplants and assessing risk of the patients developing graft-versus-host disease or characterizing such disease, comprising:

a MALDI-TOF mass spectrometer configured to conduct mass spectrometry on a blood-based sample from a patient by subjecting the sample to at least 100,000 laser shots and acquiring resulting mass spectral data;

a memory storing a reference set of mass spectral data obtained from a multitude of patients having received a transplant of PHSC or bone marrow and associated class label; and

a programmed computer configured to implement a classifier configured as a combination of filtered mini-classifiers with drop-out regularization;

wherein the reference set of mass spectral data includes feature values of at least some of the m/z features listed in Appendix A;

wherein the programmed computer is programmed to generate a class label for the sample, wherein the class label is associated with a risk of a patient providing the sample developing graft-versus-host disease or characterizing such disease.