fMRI-based studies on neurodegenerative diseases rarely report single-subject information, which is useful for assessing potential biomarkers. In a previous fMRI study, CADASIL patients showed, at the group level, a significant reduction of the long-lasting visually stimulated hyperaemic response. Here, we used data interpolation and computed a hemodynamic response function from the 20-s visual response to achieve a 40-s response prediction at the individual level. The comparison between the expected and recorded 40-s responses confirmed the occurrence of a late and frequent response reduction among patients. However, this feature was inversely related to age and was also detected in control subjects, which suggests that this potential biomarker cannot be retained for monitoring vascular dysfunction in CADASIL. We showcase an open-source analytical pipeline for single-subject analysis to quickly assess potential biomarkers in fMRI studies.
Keyphrases
- resting state
- functional connectivity
- end stage renal disease
- chronic kidney disease
- magnetic resonance imaging
- machine learning
- ejection fraction
- big data
- newly diagnosed
- electronic health record
- computed tomography
- deep learning
- prognostic factors
- mass spectrometry
- magnetic resonance
- artificial intelligence
- health information
- liquid chromatography
- social media
- patient reported outcomes