Selection of biomarkers in ME/CFS for patient stratification and treatment surveillance / optimisation

Project Details

Description

The aim of the study is to examine diagnostic potential of serum biomarkers depending on the presence or absence of viral (HHV-6, HHV-7, B19) infection biomarkers by direct comparing ME/CFS cases to healthy controls and applying the results from clinical testing and pathology to the pattern recognition algorithm random forest (RF), to widen marker patterns usable in ME/CFS patient stratification. A longer-term aim is to develop simpler diagnostic tools from routine data to assist health professionals to diagnose ME/CFS and to monitor therapeutic approaches. Examination of the diagnostic potential of serum biomarkers, both individually and in combination with viral infection markers will allow stratify ME/CFS patients and seek appropriate therapy and evaluate its efficacy. The investigation by measuring of symptom severity will also allow stratify the ME/CFS cohort into mild to severe disease classes. We hypothesize the cohort of ME/CFS patients is divided into a number of groups/subsets, one of which is a group/subset having primary autoimmune aetiology, another one which is triggered by viral infection. The group/subset triggered by viral infection could have also markers of autoimmunity. It is possible to find a set of markers of autoimmunity pointing towards ME/CFS, especially later after disease onset. It should be possible to find a set of markers allowing the stratification of ME/CFS patients according to pathomechanisms and also severity of clinical manifestations.
StatusActive
Effective start/end date1/01/2031/03/22

Keywords

  • ME/CFS,
  • clinical testing
  • markers of viral infection
  • patients stratification
  • serological biomarkers
  • machine learning

Field of Science

  • 3.5 Other medical sciences

Smart Specialization Area

  • Biomedicine, medical technologies and biotechnology

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.