Predictive test for prognosis of myelodysplastic syndrome patients using mass spectrometry of blood-based sample
Inventors
Steingrimsson, Arni • Röder, Heinrich • Röder, Joanna
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11594403-B1
Publication Date
2023-02-28
Expiration Date
Abstract
A method of predicting whether an MDS patient has a good or poor prognosis uses a general purpose computer configured as a classifier and mass-spectrometry data obtained from a blood-based sample. The classifier assigns a classification label of either Early or Late (or the equivalent) to the patient's sample. Patients classified as Early are predicted to have a poor prognosis or worse survival whereas those patients classified as Late are predicted to have a relatively better prognosis and longer survival time. The groupings demonstrated a large effect size between groups in Kaplan-Meier analysis of survival. Most importantly, while the classifications generated were correlated with other prognostic factors, such as IPSS score and genetic category, multivariate and subgroup analysis showed that they had significant independent prognostic power complementary to the existing prognostic factors.
Core Innovation
The invention performs MALDI-TOF mass spectrometry on a blood-based sample obtained from a myelodysplastic syndrome (MDS) patient by subjecting the sample to at least 100,000 laser shots and acquiring mass spectral data. A set of pre-determined mass-spectral features listed in Appendix A is used to obtain integrated intensity values from the mass spectral data, including obtaining integrated intensity values of at least 50 features listed in Appendix A. The integrated intensity values are processed to generate a diagnostic/prognostic class label using a programmed computer implementing a classifier.
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 other MDS patients and applies a classification algorithm to detect a class label for the sample. The class label indicates either relatively poor prognosis or relatively good prognosis, thereby enabling prognosis classification into defined groups. The documented development includes classifier operation based on class-labeled mass spectral data and use of a computer-implemented classification algorithm.
The invention also guides treatment decisions. When the class label indicates that the MDS patient has a relatively poor prognosis, administering hematopoietic stem cell transplants (HSCTs), high intensity chemotherapy, supportive care or combinations thereof is performed. When the class label indicates relatively good prognosis, administering lenalidomide, immunosuppressive therapy, azacytidine, or supportive therapy is performed. A further guiding embodiment predicts whether a patient is in a high risk group and supplies therapies expected to benefit patients in that high-risk classification.
Claims Coverage
The document provides three independent claims that cover classification of MDS prognosis from MALDI-TOF mass spectral data and selection of named treatment options. Across the independent claims, a core set of inventive features uses MALDI-TOF mass spectrometry with at least 100,000 laser shots, integrated intensity values for Appendix A features, and programmed-computer classification trained on class-labeled mass spectral data.
MALDI-TOF class-label detection for poor prognosis with Appendix A integrated intensities
A method detecting a class label in an MDS patient by performing MALDI-TOF mass spectrometry on a blood-based sample (at least 100,000 laser shots), obtaining integrated intensity values in the mass spectral data for a multitude of pre-determined mass-spectral features including a multitude of features listed in Appendix A (at least 50 features), and operating on the integrated intensity values with a programmed computer implementing a classifier; the classifier compares the integrated intensity values with feature values of a training set of class-labeled mass spectral data and detects a class label such that, when the class label indicates relatively poor prognosis, administering hematopoietic stem cell transplants (HSCTs), high intensity chemotherapy, supportive care or combinations thereof.
MALDI-TOF class-label detection for good prognosis with Appendix A integrated intensities
A method detecting a class label in an MDS patient by performing MALDI-TOF mass spectrometry on a blood-based sample (at least 100,000 laser shots), obtaining integrated intensity values in the mass spectral data of a multitude of pre-determined mass-spectral features including a multitude of features listed in Appendix A (at least 50 features), and operating on the integrated intensity values with a programmed computer implementing a classifier; the classifier compares the integrated intensity values with feature values of a training set of class-labeled mass spectral data and detects a class label such that, when the class label indicates relatively good prognosis, administering lenalidomide, immunosuppressive therapy, azacytidine, or supportive therapy.
Treatment guidance via classifier-developed high-risk group prediction
A method of guiding treatment of an MDS patient by performing MALDI-TOF mass spectrometry on a blood-based sample (at least 100,000 laser shots), performing a classification of the mass spectral data with a computer implementing a classifier developed from a development set of samples from other MDS patients comprising iteratively training a classifier from the development set of samples and a multitude of mass spectral features listed in Appendix A to generate a class label, and when the patient is classified into the high risk group predicting likely benefit from hematopoietic stem cell transplants (HSCTs), high intensity chemotherapy, azacytidine, decitabine, supportive care, or combinations thereof.
Collectively, the independent claims cover computer-implemented classification of MDS prognosis from MALDI-TOF mass spectral data using integrated intensity values for Appendix A features and class-labeled training data. The detected/provided class outcomes are explicitly tied to selecting named treatment options for relatively poor prognosis, relatively good prognosis, or classification into a high risk group.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?