Lupus & antiphospholipid syndrome
Combining multimodal magnetic resonance brain imaging and machine learning to unravel neurocognitive function in non-neuropsychiatric systemic lupus erythematosus
Authors' conclusion
Multimodal brain MRI demonstrated increased right amygdala perfusion that was associated with better neurocognitive performance in young SLE patients without statistically significant BBB leakage and microstructural abnormalities. A machine learning-constructed multimodal model comprising microstructural, perfusion and permeability parameters accurately predicted neurocognitive performance in SLE patients.
Study context
- Population
- Young (≤40 years) patients with SLE without neuropsychiatric manifestations and healthy controls
- Participants
- 30 vs 10
- Exposure
- SLE patients without neuropsychiatric manifestations vs healthy controls
- SLEn = 30
- Healthy controls (HCs)n = 10reference
- Outcome
- Prediction of neurocognitive function (ANAM total throughput score, TTS) by multimodal brain MRI (VBM, MTR, DCE-MRI) with machine learning
Methodological detailsmultimodal brain MRI, machine learning (glmnet)
- Multimodal brain MRI
- Machine learning (glmnet)
Main finding
As reported in the abstract
- Correlation of model-predicted with observed total throughput score (TTS) in SLE (r)
- 0.644
- P
- P < 0.0005
Observational data: associations, not effects.
Further findings
Voxel-based morphometry (VBM), magnetization transfer ratio (MTR), olfactory bulb volume, olfactory function and TTS, SLE vs HCs
- Comparable in both groups
Blood-brain barrier (BBB) permeability parameters, SLE vs HCs
- Uncorrected increase in SLE did not remain evident after correction for multiple comparisons
Right amygdala perfusion (DCE-MRI) correlation with TTS in SLE
- Positive correlation (r)
- 0.636
- P
- false discovery rate P < 0.05
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →