Magnetic resonance imaging biomarkers for the early diagnosis of Alzheimer's disease: a machine learning approach
Биомаркеры магнитно-резонансной визуализации для ранней диагностики болезни Альцгеймера: подход на основе машинного обучения
2015-09-01
SCID: 54.1/uheq3v8h
Discuss with AI
ADNI cohortAlzheimer’s diseasemachine learningmagnetic resonance imaging biomarkersmild cognitive impairment conversion
Figures from the paper
Abstract (AI)
Determination of sensitive and specific markers of very early AD progression is intended to aid researchers and clinicians to develop new treatments and monitor their effectiveness, as well as to lessen the time and cost of clinical trials. Magnetic Resonance (MR)-related biomarkers have been recently identified by the use of machine learning methods for the in vivo differential diagnosis of AD. However, the vast majority of neuroimaging papers investigating this topic are focused on the difference between AD and patients with mild cognitive impairment (MCI), not considering the impact of MCI patients who will (MCIc) or not convert (MCInc) to AD. Morphological T1-weighted MRIs of 137 AD, 76 MCIc, 134 MCInc, and 162 healthy controls (CN) selected from the Alzheimer's disease neuroimaging initiative (ADNI) cohort, were used by an optimized machine learning algorithm. Voxels influencing the classification between these AD-related pre-clinical phases involved hippocampus, entorhinal cortex, basal ganglia, gyrus rectus, precuneus, and cerebellum, all critical regions known to be strongly involved in the pathophysiological mechanisms of AD. Classification accuracy was 76% AD vs. CN, 72% MCIc vs. CN, 66% MCIc vs. MCInc (nested 20-fold cross validation). Our data encourage the application of computer-based diagnosis in clinical practice of AD opening new prospective in the early management of AD patients.
Key Findings
1
An optimized machine-learning algorithm analyzed morphological T1-weighted MRI scans from 509 ADNI participants across AD, converting MCI, non-converting MCI, and control groups.
2
Classification-relevant brain regions included the hippocampus, entorhinal cortex, basal ganglia, gyrus rectus, precuneus, and cerebellum.
3
It achieved 66% accuracy distinguishing converting from non-converting MCI patients, supporting MRI-based early-risk stratification.
4
It achieved 72% accuracy distinguishing MCI patients who converted to Alzheimer’s disease from healthy controls.
5
The algorithm achieved 76% accuracy distinguishing Alzheimer’s disease from healthy controls using nested 20-fold cross-validation.
Research Object
Morphological T1-weighted brain MRIs from Alzheimer's disease, converting and non-converting mild cognitive impairment, and healthy control groups
Research Subject
MRI-derived biomarkers and their classification performance for distinguishing early Alzheimer's disease-related stages, including conversion from mild cognitive impairment to Alzheimer's disease
Publication Details
Publication Date
2015-09-01
Journal
Publisher
ISSN
Cited by
268
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Clinical diagnosis of Alzheimer's disease1984
The diagnosis of dementia due to Alzheimer's disease: Recommendations from the National Institute on Aging‐Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease2011
The diagnosis of mild cognitive impairment due to Alzheimer's disease: Recommendations from the National Institute on Aging‐Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease2011
Mild Cognitive Impairment1999
On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation2010