Diagnostic Accuracy of MRI-Based Artificial Intelligence Models for Distinguishing Alzheimer's Disease and…

AI / informaticsDementia and neurocognitive disorders· Jul 2026

Diagnostic Accuracy of MRI-Based Artificial Intelligence Models for Distinguishing Alzheimer's Disease and Mild Cognitive Impairment From Cognitively Normal Controls: A Systematic Review and Meta-Analysis.

Sara Mahmoud Ibrahim Allaham

NeuroradiologyAI / informaticsDiagnosis

Magnetic resonance imaging-based artificial intelligence models distinguish Alzheimer's disease from normal cognition with high accuracy.

Diagnostic Accuracy of MRI-Based Artificial Intelligence Models for Distinguishing Alzheimer's Disease and Mild Cognitive Impairment From Cognitively Normal Controls: A Systematic Review and Meta-Analysis.

Sara Mahmoud Ibrahim Allaham

Dementia and neurocognitive disorders · Jul 2026

Background

Magnetic resonance imaging (magnetic resonance imaging)-based artificial intelligence (artificial intelligence) models are increasingly applied to brain magnetic resonance imaging for diagnosing Alzheimer's disease (AD) and mild cognitive impairment (mild cognitive impairment), but their overall diagnostic performance remains unclear.

Results

correctly identifies alzheimer's from normal scans nearly every time

0.96propor

Sensitivity (AD vs CN)

0.95propor

Specificity (AD vs CN)

More results

Cognitively normal tasks, predominantly using deep-learning architectures applied to Alzheimer's Disease Neuroimaging Initiative cohorts.

Cognitively normal (two studies), sensitivity was consistently high (0.91-0.93), whereas specificity varied widely (0.54-0.98), limiting the interpretability of pooled estimates.

“

Conclusion

Magnetic resonance imaging-based artificial intelligence models therefore show strong performance for established AD but heterogeneous specificity for mild cognitive impairment, underscoring the need for larger, externally validated studies in diverse populations.

Diagnostic Accuracy of MRI-Based Artificial Intelligence Models for Distinguishing Alzheimer's Disease and Mild Cognitive Impairment From Cognitively Normal Controls: A Systematic Review and Meta-Analysis.

Diagnostic Accuracy of MRI-Based Artificial Intelligence Models for Distinguishing Alzheimer's Disease and Mild Cognitive Impairment From Cognitively Normal Controls: A Systematic Review and Meta-Analysis.

Related papers