Use AI to track cognitive deviation in aged brains


Flowchart showing the framework of the brain age prediction model. In, the image data was divided into training and testing data sets. The training data set consisted of structural magnetic resonance imaging data from 974 healthy individuals, while the test data set included data from 2 groups, 231 healthy controls, and 224 aMCI subjects. B, a conventional statistical parametric mapping structural preprocessing pipe was used to generate GMV maps in the MNI space. C, the intensity values ​​of the GMV maps were extracted and concatenated to create an array of elements that were then cleaned and normalized. D, the best elastic network model was obtained by performing a supervised learning of the training data set. To optimize the hyperparameters, a grid search was performed. E, the test data set was introduced into the trained model. An age was predicted for each participant included in the test data set. PAD scores were calculated by subtracting the chronological age of the participant from their expected age. aMCI = mild amnesic cognitive impairment, GMV = gray matter volume, MNI = Montreal Neurological Institute, Dartel = Difeomorphic anatomical records using exposed lying algebra, PAD = predicted age difference. Credit: Radiological Society of North America

Researchers have developed a prediction model of brain age based on artificial intelligence (AI) to quantify deviations from a healthy trajectory of brain aging in patients with mild cognitive impairment, according to a study published in Radiology: artificial intelligence. The model can help in the early detection of cognitive impairment at the individual level.

Amnesty (aMCI) is a phase of transition from normal aging to Alzheimer’s disease (AD). People with ICM have more severe than normal memory deficits for their age and education, but not severe enough to affect daily function.

For the study, Ni Shu, Ph.D., of the State Laboratory of Cognitive Neuroscience and Learning at Beijing Normal University in Beijing, China, and colleagues used an machine learning approach to train a prediction of brain age based on T1-weighted MR images of 974 from 49.3 to 95.4 years. The trained model was applied to estimate the expected age difference (expected age vs. actual age) of patients with ICM in the Beijing Aging Brain Rejuvenation Initiative (616 healthy controls and 80 aMCI patients) and the Disease Neuroimaging Initiative Alzheimer’s (589 healthy controls and 144 aMCI patients) data sets.

The researchers also examined the associations between the predicted age difference and , genetic risk factors, pathological biomarkers of AD and clinical progression in patients with ICM.

The results showed that patients with ICM had different brain aging trajectories than the typical normal aging trajectory, and the proposed brain age prediction model could quantify individual deviations from the typical normal aging trajectory of ‘these patients. The predicted age difference was significantly associated with individual cognitive impairment of patients with ICM in several domains, including specifically memory, attention, and executive function.

“The predictive model we generated was highly accurate in estimating the chronological age in healthy participants based only on the appearance of MRI scans,” the researchers wrote. “In contrast, for aMCI, the model estimated that brain age was greater than 2.7 years on average longer than the patient’s chronological age.”

The model further demonstrated that progressive patients with aMCI show more deviations from typical normal aging than patients with stable aMCI, and the use of the predicted age difference score along with other specific AD biomarkers could better predict the progression of the MCI. Apolipoprotein E (APOE) ε4 carriers showed greater expected age differences than non-carriers, and patients with positive amyloid showed greater expected age differences than patients with negative amyloid.

The combination of the predicted age difference with other AD biomarkers showed the best performance in differentiating progressive aMCI from stable aMCI.

“This work indicates that the predicted age difference may be a robust, reliable, and computerized biomarker for early diagnosis of cognitive impairment and monitoring of response to treatment,” the authors concluded.

Exercise can slow brain deterioration from Alzheimer’s disease

More information:
Heang-Ping Chan, promise and possible traps: image recreation or generation of new images for artificial intelligence modeling. Radiology: artificial intelligence (2021). DOI: 10.1148 / ryai.2021210102

Citation: Using AI to Track Cognitive Deviation in Aged Brains (2021, June 23) Retrieved June 23, 2021 from deviation-aging.html

This document is subject to copyright. Apart from any fair treatment for private study or research purposes, no part may be reproduced without written permission. Content is provided for informational purposes only.

Source link


Please enter your comment!
Please enter your name here