Brain Age Gap Research Articles

Changes of individual BrainAGE during the course of the menstrual cycle

Brain morphology varies during the course of the menstrual cycle, with increases in individual gray matter volume at the time of ovulation. This study implemented our previously presented BrainAGE framework to analyze short-term neuroanatomical changes in healthy young women due to hormonal changes during the menstrual cycle. The BrainAGE approach determines the complex multidimensional aging pattern within the whole brain by applying established kernel regression methods to anatomical brain MRIs. The “Brain Age Gap Estimation” (i.e., BrainAGE) score is then calculated as the difference between chronological age and estimated brain age. Eight women (21–31years) completed three to four MRI scans during their menstrual cycle (i.e., at (t1) menses, (t2) time of ovulation, (t3) midluteal phase, (t4) next menses). Serum levels of estradiol and progesterone were evaluated at each scanning session.Individual BrainAGE scores significantly differed during the course of the menstrual cycle (p<0.05), with a significant decrease of −1.3years at ovulation (p<0.05). Moreover, higher estradiol levels significantly correlated with lower BrainAGE scores (r=−0.42, p<0.05). In future, the BrainAGE approach may serve as a sensitive as well as easily implementable tool to further explore the short-term and maybe long-term effects of hormones on brain plasticity and its modulating effects in lifestyle-related diseases and dementia.

Gender-specific impact of personal health parameters on individual brain aging in cognitively unimpaired elderly subjects.

Aging alters brain structure and function. Personal health markers and modifiable lifestyle factors are related to individual brain aging as well as to the risk of developing Alzheimer's disease (AD). This study used a novel magnetic resonance imaging (MRI)-based biomarker to assess the effects of 17 health markers on individual brain aging in cognitively unimpaired elderly subjects. By employing kernel regression methods, the expression of normal brain-aging patterns forms the basis to estimate the brain age of a given new subject. If the estimated age is higher than the chronological age, a positive brain age gap estimation (BrainAGE) score indicates accelerated atrophy and is considered a risk factor for developing AD. Within this cross-sectional, multi-center study 228 cognitively unimpaired elderly subjects (118 males) completed an MRI at 1.5Tesla, physiological and blood parameter assessments. The multivariate regression model combining all measured parameters was capable of explaining 39% of BrainAGE variance in males (p < 0.001) and 32% in females (p < 0.01). Furthermore, markers of the metabolic syndrome as well as markers of liver and kidney functions were profoundly related to BrainAGE scores in males (p < 0.05). In females, markers of liver and kidney functions as well as supply of vitamin B12 were significantly related to BrainAGE (p < 0.05). In conclusion, in cognitively unimpaired elderly subjects several clinical markers of poor health were associated with subtle structural changes in the brain that reflect accelerated aging, whereas protective effects on brain aging were observed for markers of good health. Additionally, the relations between individual brain aging and miscellaneous health markers show gender-specific patterns. The BrainAGE approach may thus serve as a clinically relevant biomarker for the detection of subtly abnormal patterns of brain aging probably preceding cognitive decline and development of AD.

Accelerated Brain Aging in Schizophrenia and Beyond: A Neuroanatomical Marker of Psychiatric Disorders

Structural brain abnormalities are central to schizophrenia (SZ), but it remains unknown whether they are linked to dysmaturational processes crossing diagnostic boundaries, aggravating across disease stages, and driving the neurodiagnostic signature of the illness. Therefore, we investigated whether patients with SZ (N = 141), major depression (MD; N = 104), borderline personality disorder (BPD; N = 57), and individuals in at-risk mental states for psychosis (ARMS; N = 89) deviated from the trajectory of normal brain maturation. This deviation was measured as difference between chronological and the neuroanatomical age (brain age gap estimation [BrainAGE]). Neuroanatomical age was determined by a machine learning system trained to individually estimate age from the structural magnetic resonance imagings of 800 healthy controls. Group-level analyses showed that BrainAGE was highest in SZ (+5.5 y) group, followed by MD (+4.0), BPD (+3.1), and the ARMS (+1.7) groups. Earlier disease onset in MD and BPD groups correlated with more pronounced BrainAGE, reaching effect sizes of the SZ group. Second, BrainAGE increased across at-risk, recent onset, and recurrent states of SZ. Finally, BrainAGE predicted both patient status as well as negative and disorganized symptoms. These findings suggest that an individually quantifiable "accelerated aging" effect may particularly impact on the neuroanatomical signature of SZ but may extend also to other mental disorders.

BrainAGE in Mild Cognitive Impaired Patients: Predicting the Conversion to Alzheimer’s Disease

Alzheimer’s disease (AD), the most common form of dementia, shares many aspects of abnormal brain aging. We present a novel magnetic resonance imaging (MRI)-based biomarker that predicts the individual progression of mild cognitive impairment (MCI) to AD on the basis of pathological brain aging patterns. By employing kernel regression methods, the expression of normal brain-aging patterns forms the basis to estimate the brain age of a given new subject. If the estimated age is higher than the chronological age, a positive brain age gap estimation (BrainAGE) score indicates accelerated atrophy and is considered a risk factor for conversion to AD. Here, the BrainAGE framework was applied to predict the individual brain ages of 195 subjects with MCI at baseline, of which a total of 133 developed AD during 36 months of follow-up (corresponding to a pre-test probability of 68%). The ability of the BrainAGE framework to correctly identify MCI-converters was compared with the performance of commonly used cognitive scales, hippocampus volume, and state-of-the-art biomarkers derived from cerebrospinal fluid (CSF). With accuracy rates of up to 81%, BrainAGE outperformed all cognitive scales and CSF biomarkers in predicting conversion of MCI to AD within 3 years of follow-up. Each additional year in the BrainAGE score was associated with a 10% greater risk of developing AD (hazard rate: 1.10 [CI: 1.07–1.13]). Furthermore, the post-test probability was increased to 90% when using baseline BrainAGE scores to predict conversion to AD. The presented framework allows an accurate prediction even with multicenter data. Its fast and fully automated nature facilitates the integration into the clinical workflow. It can be exploited as a tool for screening as well as for monitoring treatment options.

Advanced BrainAGE in older adults with type 2 diabetes mellitus

Aging alters brain structure and function and diabetes mellitus (DM) may accelerate this process. This study investigated the effects of type 2 DM on individual brain aging as well as the relationships between individual brain aging, risk factors, and functional measures. To differentiate a pattern of brain atrophy that deviates from normal brain aging, we used the novel BrainAGE approach, which determines the complex multidimensional aging pattern within the whole brain by applying established kernel regression methods to anatomical brain magnetic resonance images (MRI). The “Brain Age Gap Estimation” (BrainAGE) score was then calculated as the difference between chronological age and estimated brain age. 185 subjects (98 with type 2 DM) completed an MRI at 3Tesla, laboratory and clinical assessments. Twenty-five subjects (12 with type 2 DM) also completed a follow-up visit after 3.8 ± 1.5 years. The estimated brain age of DM subjects was 4.6 ± 7.2 years greater than their chronological age (p = 0.0001), whereas within the control group, estimated brain age was similar to chronological age. As compared to baseline, the average BrainAGE scores of DM subjects increased by 0.2 years per follow-up year (p = 0.034), whereas the BrainAGE scores of controls did not change between baseline and follow-up. At baseline, across all subjects, higher BrainAGE scores were associated with greater smoking and alcohol consumption, higher tumor necrosis factor alpha (TNFα) levels, lower verbal fluency scores and more severe deprepession. Within the DM group, higher BrainAGE scores were associated with longer diabetes duration (r = 0.31, p = 0.019) and increased fasting blood glucose levels (r = 0.34, p = 0.025). In conclusion, type 2 DM is independently associated with structural changes in the brain that reflect advanced aging. The BrainAGE approach may thus serve as a clinically relevant biomarker for the detection of abnormal patterns of brain aging associated with type 2 DM.

Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters

The early identification of brain anatomy deviating from the normal pattern of growth and atrophy, such as in Alzheimer's disease (AD), has the potential to improve clinical outcomes through early intervention. Recently, Davatzikos et al. (2009) supported the hypothesis that pathologic atrophy in AD is an accelerated aging process, implying accelerated brain atrophy. In order to recognize faster brain atrophy, a model of healthy brain aging is needed first. Here, we introduce a framework for automatically and efficiently estimating the age of healthy subjects from their T1-weighted MRI scans using a kernel method for regression. This method was tested on over 650 healthy subjects, aged 19–86 years, and collected from four different scanners. Furthermore, the influence of various parameters on estimation accuracy was analyzed. Our age estimation framework included automatic preprocessing of the T1-weighted images, dimension reduction via principal component analysis, training of a relevance vector machine (RVM; Tipping, 2000) for regression, and finally estimating the age of the subjects from the test samples. The framework proved to be a reliable, scanner-independent, and efficient method for age estimation in healthy subjects, yielding a correlation of r=0.92 between the estimated and the real age in the test samples and a mean absolute error of 5 years. The results indicated favorable performance of the RVM and identified the number of training samples as the critical factor for prediction accuracy. Applying the framework to people with mild AD resulted in a mean brain age gap estimate (BrainAGE) score of +10 years.