Prediction of brain age using structural magnetic resonance imaging: A comparison of accuracy and test–retest reliability of publicly available software packages

Human Brain Mapping, Journal Year: 2023, Volume and Issue: 44(17), P. 6139 - 6148

Published: Oct. 16, 2023

Brain age prediction algorithms using structural magnetic resonance imaging (MRI) aim to assess the biological of human brain. The difference between a person's chronological and estimated brain is thought reflect deviations from normal aging trajectory, indicating slower or accelerated process. Several pre-trained software packages for predicting are publicly available. In this study, we perform comparison such with respect (1) predictive accuracy, (2) test-retest reliability, (3) ability track progression over time. We evaluated six packages: brainageR, DeepBrainNet, brainage, ENIGMA, pyment, mccqrnn. accuracy reliability were assessed on MRI data 372 healthy people aged 18.4 86.2 years (mean 38.7 ± 17.5 years). All showed significant correlations predicted (r = 0.66-0.97, p < 0.001), pyment displaying strongest correlation. mean absolute error was 3.56 (pyment) 9.54 (ENIGMA). mccqrnn superior in terms (ICC values 0.94-0.98), as well longer time span. Of packages, brainageR consistently highest reliability.

Language: Английский

---

Investigating dynamic brain functional redundancy as a mechanism of cognitive reserve

Frontiers in Aging Neuroscience, Journal Year: 2025, Volume and Issue: 17

Published: Feb. 4, 2025

Introduction Individuals with higher cognitive reserve (CR) are thought to be more resilient the effects of age-related brain changes on performance. A potential mechanism CR is redundancy in network functional connectivity (BFR), which refers amount time spends a redundant state, indicating presence multiple independent pathways between regions. These can serve as back-up information processing routes, providing resiliency stress or disease. In this study we aimed investigate whether BFR modulates association and performance across broad range domains. Methods An open-access neuroimaging behavioral dataset ( n = 301 healthy participants, 18–89 years) was analyzed. Cortical gray matter (GM) volume, cortical thickness age, extracted from structural T1 images, served our measures life-course related (BC). Cognitive scores were principal component analysis performed 13 tests Multivariate linear regression tested modulating effect relationship Results PCA revealed three test components episodic, semantic executive functioning. Increased predicted reduced episodic functioning when considering GM volume BC. significantly modulated We found neither predictive nor performance, significant defining BC via age. Discussion Our results suggest that could metric certain domains, specifically functioning, defined dimensions findings potentially indicate underlying mechanisms CR.

Language: Английский

---

A perspective on brain-age estimation and its clinical promise

Nature Computational Science, Journal Year: 2024, Volume and Issue: 4(10), P. 744 - 751

Published: July 24, 2024

Language: Английский

---

Examining the reliability of brain age algorithms under varying degrees of participant motion

Brain Informatics, Journal Year: 2024, Volume and Issue: 11(1)

Published: April 4, 2024

Abstract Brain age algorithms using data science and machine learning techniques show promise as biomarkers for neurodegenerative disorders aging. However, head motion during MRI scanning may compromise image quality influence brain estimates. We examined the effects of on predictions in adult participants with low, high, no scans ( Original N = 148; Analytic 138 ). Five popular were tested: brainageR, DeepBrainNet, XGBoost, ENIGMA, pyment. Evaluation metrics, intraclass correlations (ICCs), Bland–Altman analyses assessed reliability across conditions. Linear mixed models quantified effects. Results demonstrated significantly impacted estimates some algorithms, ICCs dropping low 0.609 errors increasing up to 11.5 years high scans. DeepBrainNet pyment showed greatest robustness (ICCs 0.956–0.965). XGBoost brainageR had largest (up 13.5 RMSE) bias motion. Findings indicate artifacts significant ways. Furthermore, our results suggest certain like be preferable deployment populations where acquisition is likely. Further optimization validation critical use a biomarker relevant clinical outcomes.

Language: Английский

---

Brain Age Gap Reduction Following Physical Exercise Mirrors Negative Symptom Improvement in Schizophrenia Spectrum Disorders

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 8, 2025

Abstract Schizophrenia spectrum disorders (SSD) are associated with accelerated brain aging, reflected in an increased age gap. This gap serves as a biomarker, indicating poorer health, cognitive deficits, and greater severity specific symptom domains. Physical exercise holds promise adjunct therapy to mitigate these deficits by potentially promoting recovery. However, the extent of overall improvements health following exercise, along their predictors relationships clusters, yet be determined. study examined metric quantitative indicator recovery response physical exercise. To achieve this, we aggregated data from two randomized controlled trials, analyzing baseline ( n = 134) 3- or 6-month post-exercise 46) individuals SSD. Our findings revealed that patients higher BMI demonstrated recovery, evidenced reduced post-exercise. Furthermore, changes were negative symptoms cognition, suggesting reductions brain-predicted may reflect relief, particularly domains beyond positive symptoms. These results underscore importance support using surrogate marker for tracking clinically relevant highlight need stratified interventions combined lifestyle modifications enhance outcomes Glossary (SSD): Mental conditions characterized psychosis, alteration perception reality. Cardinal include hallucinations (sensory not mirroring reality) delusions (persistent beliefs rooted reality). Positive symptoms: A cluster SSD including complaints distinctively present patiens: hallucinations, delusions, thought disorder (disorganized thinking speech). Negative absent loss interest, motivation, enjoyment, social interactions, flattened affect. Cognitive Another attention, executive function, memory. Biomarker: Objective, quantifiable indicators biological states processes used predict, diagnose, treat illnesses. Brain gap: biomarker aging. Brain-predicted is predicted machine learning algorithm based on imaging data. Subtracting chronological gap, where values indicate aging brain. Neuroplasticity: The brain’s ability reorganize itself through new synaptic connections learning, treatment, injury. Randomized Controlled Trials (RCTs): design randomly assigns participants experimental group control test efficacy intervention.

Language: Английский

---

Brain Age as a New Measure of Disease Stratification in Huntington's Disease

Movement Disorders, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 28, 2025

Abstract Background Despite advancements in understanding Huntington's disease (HD) over the past two decades, absence of disease‐modifying treatments remains a challenge. Accurately characterizing progression states is crucial for developing effective therapeutic interventions. Various factors contribute to this challenge, including need precise methods that can account complex nature HD progression. Objective This study aims address gap by leveraging concept brain's biological age as foundation data‐driven clustering method delineate various Brain‐predicted age, influenced somatic expansion and its impact on brain volumes, offers promising avenue stratification stratifying subgroups determining optimal timing Methods To achieve this, data from 953 participants across diverse cohorts, PREDICT‐HD, TRACK‐HD, IMAGE‐HD, were meticulously analyzed. was computed using sophisticated algorithms, categorized into four groups based CAG product score. Unsupervised k‐means with brain‐predicted difference (brain‐PAD) then employed identify distinct states. Results The analysis revealed significant disparities between controls, these differences becoming more pronounced progressed. Brain‐PAD demonstrated correlation severity, effectively identifying five characterized longitudinal disparities. Conclusions These findings highlight potential brain‐PAD capturing states, thereby enhancing prognostic methodologies providing valuable insights future clinical trial designs © 2025 Author(s). Movement Disorders published Wiley Periodicals LLC behalf International Parkinson Disorder Society.

Language: Английский

---

White matter injuries mediate brain age effects on cognitive function in cerebral small vessel disease

Neuroradiology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 17, 2025

This study aims to investigate the potential effect of compromised structural integrity on cerebral aging and cognitive function in small vessel disease (CSVD). Fifty-five CSVD patients 42 controls underwent three-dimensional T1-weighted imaging diffusion tensor imaging. Relative brain age (RBA) was computed assess aging. Variables included cortical thickness, volume, white matter hyperintensity (WMH) peak width skeletonized mean diffusivity (PSMD), ventricular choroid plexus volume. Mini-Mental State Examination (MMSE) conducted general cognition. Trail Making Test (TMT) Auditory Verbal Learning were administered evaluate executive episodic memory, respectively. Mediation analysis multivariate linear regression with interaction terms performed explore differential impacts RBA between controls. significantly increased compared (p < 0.001). White injuries as assessed PSMD (mediation magnitude: 41.1%) WMH volume 56.9%) mediated relationship pathologies Higher correlated poorer scores MMSE, TMT-A, TMT-B 0.01). Additionally, 57.8% 48.3% 28.8% TMT-B) 55.1% MMSE) 0.05). play a critical role decline patients.

Language: Английский

---

Brain Aging in Specific Phobia: An ENIGMA-Anxiety Mega-Analysis

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: March 20, 2025

Specific phobia (SPH) is a prevalent anxiety disorder and may involve advanced biological aging. However, brain age research in psychiatry has primarily examined mood psychotic disorders. This mega-analysis investigated aging SPH participants within the ENIGMA-Anxiety Working Group. 3D s tructural MRI scans from 17 international samples (600 individuals, of whom 504 formally diagnosed 96 questionnaire-based cases; 1,134 controls; range: 22-75 years) were processed with FreeSurfer. Brain was estimated 77 subcortical cortical regions publicly available ENIGMA model. The brain-predicted difference (brain-PAD) calculated as minus chronological age. Linear mixed-effect models group differences brain-PAD moderation by No significant manifested ( β diagnosis (SE)=0.37 years (0.43), p =0.39). A negative diagnosis-by-age interaction identified, which most pronounced =-0.08 (0.03), pFDR =0.02). remained when excluding comorbidities, depressive medication use. Post-hoc analyses revealed for formal younger (22-35 years; =1.20 (0.60), <0.05, mixed-effects d (95% confidence interval)=0.14 (0.00-0.28)), but not older (36-75 =0.07 (0.65), =0.91). did relate to full sample. observed across analyses, strongest SPH. showed subtle young adults Taken together, these findings indicate importance clinical severity, impairment persistence, suggest slightly earlier end maturational processes or decline structure

Language: Английский

---

Longitudinal brain age in first-episode mania youth treated with lithium or quetiapine

European Neuropsychopharmacology, Journal Year: 2025, Volume and Issue: 95, P. 40 - 48

Published: April 14, 2025

It is unclear if lithium and quetiapine have neuroprotective effects, especially in early stages of bipolar schizoaffective disorders. Here, an age-related multivariate brain structural measure (i.e., brain-PAD) at baseline changes response to treatment after a first-episode mania (FEM) were examined. FEM participants randomized (n=21) or (n=18) monotherapy. T1-weighted scans acquired baseline, 3-months (FEM only) 12-months. Brain age predictions for healthy controls (n=29) young people with disorder (15-25 years) derived using deep learning model trained on one the largest datasets (N=53,542) date. Notably, higher brain-PAD value (predicted - age) signifies older-appearing brain. Baseline was compared (+1.70 year, p=0.04; Cohen's d=0.53 [SE=0.25], CI 95% [0.04 1.01]). However, no significant effects time group, nor interaction between two, observed throughout course study. did not predict any change symptomatic, quality life functional outcome scores over 12 months. In individuals FEM, findings show their brains appeared older than controls. remained stable across groups neither values predicted 12-month outcomes. A longer follow-up larger sample warranted determine emerge later TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry ACTRN12607000639426.

Language: Английский

---

Volumetric Changes in Cerebellar Transverse Zones: Age and Sex Effects in Health and Neurological Disorders

Human Brain Mapping, Journal Year: 2025, Volume and Issue: 46(6)

Published: April 15, 2025

Cerebellar volumetric changes are intricately linked to aging, with distinct patterns across its transverse zones, the functional subdivisions characterized by unique cytoarchitectural and connectivity profiles. Despite research efforts, cerebellar aging process in health neurological disorders remains poorly understood. In this study, we investigated effects of age sex on total cerebellum, zone, lobule volumes using MRI data from over 45,000 participants compiled six neuroimaging datasets. We also propose a framework for estimating cerebellum as an indicator health. Significant age-dependent volume reductions were observed central zone (CZ; lobules VI VII) exhibiting steepest decline both disorders. This finding highlights CZ's vulnerability critical role cognitive emotional processing. found prominent differences changes. Males exhibited smaller intracranial (TIV)-adjusted faster reduction than females mild impairment (MCI), Alzheimer disease (AD), Parkinson (PD). contrast, schizophrenia (SZ) cocaine use disorder (CUD) revealed males. Patients MCI, AD, PD experienced more pronounced atrophy posterior (PZ) nodular (NZ) zones compared age-matched healthy controls, while SZ patients CZ. CUD, non-significant was all controls. Moreover, our notable difference between individuals patients. Finally, charted individuals, focusing capturing subdivisions. These findings underscore potential analysis biomarker early detection monitoring neurodegenerative neuropsychiatric Our novel approach complements enhances MRI-based analyses, providing essential insights into pathogenesis neurodegeneration, chronic conditions.

Language: Английский

---