Patent · US Active

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

US9563744B1 · kind B1 · utility

6Cited by
5References
11Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 23, 2015
Grant dateFeb 7, 2017
Priority date—
Expiry dateNov 23, 2035

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH01J49/40
  • WIPO fieldMeasurement
  • WIPO sectorInstruments

Abstract

A classifier and method for predicting or characterizing graft-versus-host disease in a patient after receiving a transplant of pluripotent hematopoietic stem cells or bone marrow. The classifier operates on mass-spectral data obtained from a blood-based sample of the patient and is configured as a combination of filtered mini-classifiers using a regularized combination method, such as logistic regression with extreme drop-out. The method also uses a “deep-MALDI” mass spectrometry technique in which the blood-based samples are subject to at least 100,000 laser shots in MALDI-TOF mass spectrometry in order to reveal greater spectral content and detect low abundance proteins circulating in serum associated with graft-versus-host disease.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.