Biodesix has filed a patent for a method of predicting the prognosis of patients with myelodysplastic syndrome (MDS). The method involves using mass-spectrometry data obtained from a blood-based sample and a computer classifier to assign a classification label of either “Early” or “Late” to the patient’s sample. Patients classified as “Early” are predicted to have a poor prognosis, while those classified as “Late” are predicted to have a better prognosis and longer survival time. The method has shown significant independent prognostic power, complementing existing prognostic factors. GlobalData’s report on Biodesix gives a 360-degree view of the company including its patenting strategy. Buy the report here.
According to GlobalData’s company profile on Biodesix, AI-assisted drug screening was a key innovation area identified from patents. Biodesix's grant share as of June 2023 was 1%. Grant share is based on the ratio of number of grants to total number of patents.
Method for predicting prognosis of mds patients using mass spectrometry
A recently filed patent (Publication Number: US20230197426A1) describes a method for predicting the prognosis of patients with myelodysplastic syndrome (MDS). The method involves performing MALDI-TOF mass spectrometry on a blood-based sample obtained from the MDS patient, acquiring mass spectral data, and obtaining integrated intensity values of pre-determined mass-spectral features. These integrated intensity values are then processed by a programmed computer implementing a classifier. The classifier compares the integrated intensity values with feature values from a training set of class-labeled mass spectral data obtained from other MDS patients and generates a class label associated with the prognosis of the MDS patient.
The patent also describes a classifier for predicting the prognosis of MDS patients. The classifier includes a memory storing a reference set of mass spectral data obtained from blood-based samples of multiple MDS patients and a programmed computer configured to implement a classifier as a combination of filtered mini-classifiers with drop-out regularization. The reference set of mass spectral data includes feature values of specific mass-to-charge ratio (m/z) features listed in Appendix A.
Additionally, the patent describes a laboratory testing system for conducting tests on blood-based samples from MDS patients and predicting their prognosis. The system includes a MALDI-TOF mass spectrometer for conducting mass spectrometry on the blood-based sample, a memory storing a reference set of mass spectral data obtained from multiple MDS patients, and a programmed computer implementing a classifier. The programmed computer generates a class label for the sample based on the reference set and the resulting mass spectral data, which is associated with the prognosis of the MDS patient.
Overall, this patent presents a method, classifier, and laboratory testing system for predicting the prognosis of MDS patients using MALDI-TOF mass spectrometry and integrated intensity values of specific mass-spectral features. By comparing the patient's data with a training set, the classifier can generate a class label associated with the patient's prognosis. This technology has the potential to improve the accuracy and efficiency of prognosis prediction for MDS patients, aiding in personalized treatment decisions.