Sindhuja T Govindarajan, PhD
@sindhujatg.bsky.social
These findings contribute to ongoing efforts in early detection and understanding of brain health, with potential implications for personalized risk assessment and targeted interventions during the crucial mid-life window.
March 21, 2025 at 2:31 PM
These findings contribute to ongoing efforts in early detection and understanding of brain health, with potential implications for personalized risk assessment and targeted interventions during the crucial mid-life window.
Our ML-based MRI markers:
- outperformed conventional structural MRI with a ten-fold increase in effect sizes.
- captured subtle patterns at sub-clinical stages.
- were most sensitive in mid-life (45-64 years).
- showed stronger associations with cognitive performance than diagnosis alone.
- outperformed conventional structural MRI with a ten-fold increase in effect sizes.
- captured subtle patterns at sub-clinical stages.
- were most sensitive in mid-life (45-64 years).
- showed stronger associations with cognitive performance than diagnosis alone.
March 21, 2025 at 2:31 PM
Our ML-based MRI markers:
- outperformed conventional structural MRI with a ten-fold increase in effect sizes.
- captured subtle patterns at sub-clinical stages.
- were most sensitive in mid-life (45-64 years).
- showed stronger associations with cognitive performance than diagnosis alone.
- outperformed conventional structural MRI with a ten-fold increase in effect sizes.
- captured subtle patterns at sub-clinical stages.
- were most sensitive in mid-life (45-64 years).
- showed stronger associations with cognitive performance than diagnosis alone.
We found that these in silico severity markers are most sensitive in mid-life and offer insights into how these factors impact brain structure, enabling individual estimation of brain changes.
#Neuroimaging #BrainMRI #MachineLearning #MidlifeHealth #CardiovascularRisk #Alzheimers #Dementia
#Neuroimaging #BrainMRI #MachineLearning #MidlifeHealth #CardiovascularRisk #Alzheimers #Dementia
March 21, 2025 at 2:31 PM
We found that these in silico severity markers are most sensitive in mid-life and offer insights into how these factors impact brain structure, enabling individual estimation of brain changes.
#Neuroimaging #BrainMRI #MachineLearning #MidlifeHealth #CardiovascularRisk #Alzheimers #Dementia
#Neuroimaging #BrainMRI #MachineLearning #MidlifeHealth #CardiovascularRisk #Alzheimers #Dementia
To address this, we developed individual MRI-based markers using machine learning to quantify the structural differences in the brain related to hypertension, hyperlipidemia, smoking, obesity, and type-2 diabetes mellitus from 37K+ individuals aged 45-85.
March 21, 2025 at 2:31 PM
To address this, we developed individual MRI-based markers using machine learning to quantify the structural differences in the brain related to hypertension, hyperlipidemia, smoking, obesity, and type-2 diabetes mellitus from 37K+ individuals aged 45-85.