Back

Brain age prediction improves the early detection of Alzheimer's disease in East Asian elderly

Choi, U.-S.; Park, J. Y.; Lee, J. J.; Choi, K. Y.; Won, S.; Lee, K. H.

2023-03-03 radiology and imaging
10.1101/2023.02.28.23286588 medRxiv
Show abstract

IntroductionBrain age prediction is used to quantify the pathological and cognitive changes associated with brain aging. However, the predicted age derived from certain models can result in biased estimation and the concealment of inherent aged brain function. MethodsWe constructed a brain age prediction model for the East Asian elderly brain using the brain volume and cortical thickness features from cognitively normal (CN) brains. Furthermore, our model was used to estimate different diagnoses and to construct a classification model of mild cognitive impairment (MCI) conversion and Alzheimers disease (AD) conversion. ResultsOur model showed a strong association of the brain age difference (BAD) with three diagnosis groups. In addition, the classification models of MCI conversion and AD conversion showed acceptable and robust performances, respectively (area under the curve [AUC] = 0.66, AUC = 0.76). DiscussionWe believe that our model can be used to estimate the predicted status of an East Asian elderly brain. Moreover, the MCI conversion model has the potential to prevent severe cognitive impairment and can be used for the early detection of AD.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Alzheimer's Research & Therapy
○ 57 papers in training set
Top 0.1%
19.0%
Similar papers in this journal
2
Journal of Alzheimer's Disease
○ 48 papers in training set
Top 0.1%
15.5%
Similar papers in this journal
3
PLOS ONE
● 5266 papers in training set
Top 17%
10.1%
Similar papers in this journal
4
Scientific Reports
○ 3612 papers in training set
Top 18%
5.0%
Similar papers in this journal
5
Experimental Gerontology
○ 12 papers in training set
Top 0.1%
2.9%
Similar papers in this journal
50% of probability mass above
6
Frontiers in Aging Neuroscience
○ 74 papers in training set
Top 0.5%
2.5%
7
Informatics in Medicine Unlocked
○ 22 papers in training set
Top 0.4%
2.5%
8
BMC Geriatrics
○ 18 papers in training set
Top 0.2%
2.5%
9
Human Brain Mapping
○ 329 papers in training set
Top 3%
1.8%
10
Frontiers in Neuroscience
○ 256 papers in training set
Top 3%
1.8%
11
Aging
○ 75 papers in training set
Top 0.9%
1.5%
12
Neurobiology of Aging
○ 107 papers in training set
Top 0.9%
1.5%
13
Alzheimer's & Dementia: Translational Research & Clinical Interventions
○ 17 papers in training set
Top 0.3%
1.5%
14
Brain Sciences
○ 55 papers in training set
Top 0.9%
1.5%
15
Heliyon
○ 152 papers in training set
Top 4%
1.4%
16
NeuroImage
○ 903 papers in training set
Top 5%
1.2%
17
Journal of Alzheimer’s Disease
○ 50 papers in training set
Top 0.9%
1.2%
18
The Journals of Gerontology, Series A: Biological Sciences and Medical Sciences
◐ 26 papers in training set
Top 0.3%
1.2%
19
Frontiers in Computational Neuroscience
○ 60 papers in training set
Top 0.9%
1.2%
20
Alzheimer's & Dementia
177 papers in training set
Top 2%
1.1%
21
Diagnostics
○ 50 papers in training set
Top 2%
1.1%
22
JMIRx Med
◐ 32 papers in training set
Top 2%
1.1%
23
Neuroscience
○ 97 papers in training set
Top 2%
0.9%
24
Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
○ 42 papers in training set
Top 0.9%
0.9%
25
Brain Structure and Function
○ 93 papers in training set
Top 1%
0.9%
26
Healthcare
○ 17 papers in training set
Top 0.9%
0.9%
27
Journal of Magnetic Resonance Imaging
○ 16 papers in training set
Top 0.3%
0.9%
28
Frontiers in Neurology
○ 102 papers in training set
Top 3%
0.9%
29
Journal of the Neurological Sciences
○ 18 papers in training set
Top 0.6%
0.6%
30
Brain Stimulation
○ 125 papers in training set
Top 1%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.