T1-weighted MRI-driven Brain Age Estimation in Alzheimer's Disease and Parkinson's Disease

Advanced brain ageing in Parkinson's disease is related to disease duration and individual impairment

Machine learning can reliably predict individual age from MRI data, revealing that patients with neurodegenerative disorders show an elevated biological age. A surprising gap in the literature, however, pertains to Parkinson's disease. Here, we evaluate brain age in two cohorts of Parkinson's patients and investigated the relationship between individual brain age and clinical characteristics. We assessed 372 patients with idiopathic Parkinson's disease, newly diagnosed cases from the Parkinson's Progression Marker Initiative database and a more chronic local sample, as well as age- and sex-matched healthy controls. Following morphometric preprocessing and atlas-based compression, individual brain age was predicted using a multivariate machine learning model trained on an independent, multi-site reference sample. Across cohorts, healthy controls were well predicted with a mean error of 4.4 years. In turn, Parkinson's patients showed a significant (controlling for age, gender and site) increase in brain age of ∼3 years. While this effect was already present in the newly diagnosed sample, advanced biological age was significantly related to disease duration as well as worse cognitive and motor impairment. While biological age is increased in patients with Parkinson's disease, the effect is at the lower end of what is found for other neurological and psychiatric disorders. We argue that this may reflect a heterochronicity between forebrain atrophy and small but behaviourally salient midbrain pathology. Finally, we point to the need to disentangle physiological ageing trajectories, lifestyle effects and core pathological changes.

Brain age and Alzheimer's-like atrophy are domain-specific predictors of cognitive impairment in Parkinson's disease

Recently, it was shown that patients with Parkinson's disease (PD) who exhibit an "Alzheimer's disease (AD)-like" pattern of brain atrophy are at greater risk for future cognitive decline. This study aimed to investigate whether this association is domain-specific and whether atrophy associated with brain aging also relates to cognitive impairment in PD. SPARE-AD, an MRI index capturing AD-like atrophy, and atrophy-based estimates of brain age were computed from longitudinal structural imaging data of 178 PD patients and 84 healthy subjects from the LANDSCAPE cohort. All patients underwent an extensive neuropsychological test battery. Patients diagnosed with mild cognitive impairment or dementia were found to have higher SPARE-AD scores as compared to patients with normal cognition and healthy controls. All patient groups showed increased brain age. SPARE-AD predicted impairment in memory, language and executive functions, whereas advanced brain age was associated with deficits in attention and working memory. Data suggest that SPARE-AD and brain age are differentially related to domain-specific cognitive decline in PD. The underlying pathomechanisms remain to be determined.

The influence of white matter hyperintensity on cognitive impairment in Parkinson's disease

The aim of this meta‐analysis was to review systematically and to identify the relationship between the severity and location of white matter hyperintensities (WMHs) and the degree of cognitive decline in patients with Parkinson’s disease (PD). We searched the PubMed, EMBASE, Web of Science, Ovid, and Cochrane Library databases for clinical trials of the severity and location of WMHs on the degree of cognitive impairment in PD through October 2020. We conducted the survey to compare the association of WMH burden in patients with PD with mild cognitive impairment (PD‐MCI) versus those with normal cognition (PD‐NC) and in patients with PD with dementia (PDD) versus those with PD without dementia (PD‐ND). Nine studies with PD‐MCI versus PD‐NC and 10 studies with PDD versus PD‐ND comparisons were included. The WMH burden in PD‐MCI patients was significantly different compared to that in PD‐NC patients (standard mean difference, SMD = 0.39, 95% CI: 0.12 to 0.66, p = 0.005), while there was no correlation shown in the age‐matched subgroup of the comparison. In addition, PDD patients had a significantly higher burden of WMHs (SMD = 0.8, 95% CI: 0.44 to 1.71, p < 0.0001), especially deep white matter hyperintensities (SMD = 0.54, 95% CI: 0.36 to 0.73, p < 0.00001) and periventricular hyperintensities (SMD = 0.70, 95% CI: 0.36 to 1.04, p < 0.0001), than PD‐NC patients, regardless of the adjustment of age. WMHs might be imaging markers for cognitive impairment in PDD but not in PD‐MCI, regardless of age, vascular risk factors, or race. Further prospective studies are needed to validate the conclusions.

Classification-Biased Apparent Brain Age for the Prediction of Alzheimer's Disease

Machine Learning methods are often adopted to infer useful biomarkers for the early diagnosis of many neurodegenerative diseases and, in general, of neuroanatomical ageing. Some of these methods estimate the subject age from morphological brain data, which is then indicated as “brain age”. The difference between such a predicted brain age and the actual chronological age of a subject can be used as an indication of a pathological deviation from normal brain ageing. An important use of the brain age model as biomarker is the prediction of Alzheimer's disease (AD) from structural Magnetic Resonance Imaging (MRI). Many different machine learning approaches have been applied to this specific predictive task, some of which have achieved high accuracy at the expense of the descriptiveness of the model. This work investigates an appropriate combination of data science techniques and linear models to provide, at the same time, high accuracy and good descriptiveness. The proposed method is based on a data workflow that include typical data science methods, such as outliers detection, feature selection, linear regression, and logistic regression. In particular, a novel inductive bias is introduced in the regression model, which is aimed at improving the accuracy and the specificity of the classification task. The method is compared to other machine learning approaches for AD classification based on morphological brain data with and without the use of the brain age, including Support Vector Machines and Deep Neural Networks. This study adopts brain MRI scans of 1, 901 subjects which have been acquired from three repositories (ADNI, AIBL, and IXI). A predictive model based only on the proposed apparent brain age and the chronological age has an accuracy of 88% and 92%, respectively, for male and female subjects, in a repeated cross-validation analysis, thus achieving a comparable or superior performance than state of the art machine learning methods. The advantage of the proposed method is that it maintains the morphological semantics of the input space throughout the regression and classification tasks. The accurate predictive model is also highly descriptive and can be used to generate potentially useful insights on the predictions.

Predicting brain age using machine learning algorithms: A comprehensive evaluation

Machine learning (ML) algorithms play a vital role in brain age estimation frameworks. The impact of regression algorithms on prediction accuracy in the brain age estimation frameworks have not been comprehensively evaluated. Here, we sought to assess the efficiency of different regression algorithms on brain age estimation. To this end, we built a brain age estimation framework based on a large set of cognitively healthy (CH) individuals (N = 788) as a training set followed by different regression algorithms (18 different algorithms in total). We then quantified each regression-algorithm on independent test sets composed of 88 CH individuals, 70 mild cognitive impairment patients as well as 30 Alzheimers disease patients. The prediction accuracy in the independent test set (i.e., CH set) varied in regression algorithms (mean absolute error (MAE) from 4.63 to 7.14 yrs, R2 from 0.76 to 0.88). The highest and lowest prediction accuracies were achieved by Quadratic Support Vector Regression algorithm (MAE = 4.63 yrs, R2 = 0.88, 95% CI = [-1.26, 1.42]) and Binary Decision Tree algorithm (MAE = 7.14 yrs, R2 = 0.76, 95% CI = [-1.50, 2.62]), respectively. Our experimental results demonstrate that prediction accuracy in brain age frameworks is affected by regression algorithms, indicating that advanced machine learning algorithms can lead to more accurate brain age predictions in clinical settings.

Motor Progression in Early-Stage Parkinson's Disease: A Clinical Prediction Model and the Role of Cerebrospinal Fluid Biomarkers

Background: The substantial heterogeneity of clinical symptoms and lack of reliable progression markers in Parkinson's disease (PD) present a major challenge in predicting accurate progression and prognoses. Increasing evidence indicates that each component of the neurovascular unit (NVU) and blood-brain barrier (BBB) disruption may take part in many neurodegenerative diseases. Since some portions of CSF are eliminated along the neurovascular unit and across the BBB, disturbing the pathways may result in changes of these substances.

Methods: Four hundred seventy-four participants from the Parkinson's Progression Markers Initiative (PPMI) study (NCT01141023) were included in the study. Thirty-six initial features, including general information, brief clinical characteristics and the current year's classical scale scores, were used to build five regression models to predict PD motor progression represented by the coming year's Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III score after redundancy removal and recursive feature elimination (RFE)-based feature selection. Then, a threshold range was added to the predicted value for more convenient model application. Finally, we evaluated the CSF and blood biomarkers' influence on the disease progression model.

Results: Eight hundred forty-nine cases were included in the study. The adjusted R² values of three different categories of regression model, linear, Bayesian and ensemble, all reached 0.75. Models of the same category shared similar feature combinations. The common features selected among the categories were the MDS-UPDRS Part III score, Montreal Cognitive Assessment (MOCA) and Rapid Eye Movement Sleep Behavior Disorder Questionnaire (RBDSQ) score. It can be seen more intuitively that the model can achieve certain prediction effect through threshold range. Biomarkers had no significant impact on the progression model within the data in the study.

Conclusions: By using machine learning and routinely gathered assessments from the current year, we developed multiple dynamic models to predict the following year's motor progression in the early stage of PD. These methods will allow clinicians to tailor medical management to the individual and identify at-risk patients for future clinical trials examining disease-modifying therapies.

Multimodal imaging improves brain age prediction and reveals distinct abnormalities in patients with psychiatric and neurological disorders

The deviation between chronological age and age predicted using brain MRI is a putative marker of overall brain health. Age prediction based on structural MRI data shows high accuracy in common brain disorders. However, brain aging is complex and heterogenous, both in terms of individual differences and the underlying biological processes. Here, we implemented a multimodal model to estimate brain age using different combinations of cortical area, thickness and sub‐cortical volumes, cortical and subcortical T1/T2‐weighted ratios, and cerebral blood flow (CBF) based on arterial spin labeling. For each of the 11 models we assessed the age prediction accuracy in healthy controls (HC, n = 750) and compared the obtained brain age gaps (BAGs) between age‐matched subsets of HC and patients with Alzheimer's disease (AD, n = 54), mild (MCI, n = 90) and subjective (SCI, n = 56) cognitive impairment, schizophrenia spectrum (SZ, n = 159) and bipolar disorder (BD, n = 135). We found highest age prediction accuracy in HC when integrating all modalities. Furthermore, two‐group case–control classifications revealed highest accuracy for AD using global T1‐weighted BAG, while MCI, SCI, BD and SZ showed strongest effects in CBF‐based BAGs. Combining multiple MRI modalities improves brain age prediction and reveals distinct deviations in patients with psychiatric and neurological disorders. The multimodal BAG was most accurate in predicting age in HC, while group differences between patients and HC were often larger for BAGs based on single modalities. These findings indicate that multidimensional neuroimaging of patients may provide a brain‐based mapping of overlapping and distinct pathophysiology in common disorders.

P2X4R Overexpression Upregulates Interleukin-6 and Exacerbates 6-OHDA-Induced Dopaminergic Degeneration in a Rat Model of PD

The pathogenesis of Parkinson’s disease (PD) remains elusive. Current thinking suggests that the activation of microglia and the subsequent release of inflammatory factors, including interleukin-6 (IL-6), are involved in the pathogenesis of PD. P2X4 receptor (P2X4R) is a member of the P2X superfamily of ion channels activated by ATP. To study the possible effect of the ATP-P2X4R signal axis on IL-6 in PD, lentivirus carrying the P2X4R-overexpression gene or empty vector was injected into the substantia nigra (SN) of rats, followed by treatment of 6-hydroxydopamine (6-OHDA) or saline 1 week later. The research found the relative expression of P2X4R in the 6-OHDA-induced PD rat models was notably higher than that in the normal. And P2X4R overexpression could upregulate the expression of IL-6, reduce the amount of dopaminergic (DA) neurons in the SN of PD rats, suggesting that P2X4R may mediate the production of IL-6 to damage DA neurons in the SN. Our data revealed the important role of P2X4R in modulating IL-6, which leads to neuroinflammation involved in PD pathogenesis.

Various Diseases and Clinical Heterogeneity Are Associated With "Hot Cross Bun"

Objective: To characterize the clinical phenotypes associated with the "hot cross bun" sign (HCBs) on MRI and identify correlations between neuroimaging and clinical characteristics. Methods: Firstly, we screened a cohort of patients with HCBs from our radiologic information system (RIS) in our center. Secondly, we systematically reviewed published cases on HCBs and classified all these cases according to their etiologies. Finally, we characterized all HCBs cases in detail and classified the disease spectra and their clinical heterogeneity. Results: Out of a total of 3,546 patients who were screened, we identified 40 patients with HCBs imaging sign in our cohort; systemic literature review identified 39 cases, which were associated with 14 diseases. In our cohort, inflammation [neuromyelitis optica spectrum disorders (NMOSD), multiple sclerosis (MS), and acute disseminated encephalomyelitis (ADEM)] and toxicants [toxic encephalopathy caused by phenytoin sodium (TEPS)] were some of the underlying etiologies. Published cases by systemic literature review were linked to metabolic abnormality, degeneration, neoplasm, infection, and stroke. We demonstrated that the clinical phenotype, neuroimaging characteristics, and HCBs response to therapy varied greatly depending on underlying etiologies. Conclusion: This is the first to report HCBs spectra in inflammatory and toxication diseases. Our study and systemic literature review demonstrated that the underpinning disease spectrum may be broader than previously recognized.

More Sensitive Identification for Bradykinesia Compared to Tremors in Parkinson's Disease Based on Parkinson's KinetiGraph (PKG)

The effective management and therapies for Parkinson's disease (PD) require appropriate clinical evaluation. The Parkinson's KinetiGraph (PKG) is a wearable sensor system that can monitor the motion characteristics of PD objectively and continuously. This study was aimed to assess the correlations between PKG data and clinical scores of bradykinesia, rigidity, tremor, and fluctuation. It also aims to explore the application value of identifying early motor symptoms. An observational study of 100 PD patients wearing the PKG for ≥ 6 days was performed. It provides a series of data, such as the bradykinesia score (BKS), percent time tremor (PTT), dyskinesia score (DKS), and fluctuation and dyskinesia score (FDS). PKG data and UPDRS scores were analyzed, including UPDRS III total scores, UPDRS III-bradykinesia scores (UPDRS III-B: items 23-26, 31), UPDRS III-rigidity scores (UPDRS III-R: item 22), and scores from the Wearing-off Questionnaire (WOQ-9). This study shows that there was significant correlation between BKS and UPDRS III scores, including UPDRS III total scores, UPDRS III-B, and UPDRS III-R scores (r = 0.479-0.588, p ≤ 0.001), especially in the early-stage group (r = 0.682, p < 0.001). Furthermore, we found that BKS in patients with left-sided onset (33.57 ± 5.14, n = 37) is more serious than in patients with right-sided onset (29.87 ± 6.86, n = 26). Our findings support the feasibility of using the PKG to detect abnormal movements, especially bradykinesia in PD. It is suitable for the early detection, remote monitoring, and timely treatment of PD symptoms.

The Effects of Transcranial Direct Current Stimulation (tDCS) on Balance Control in Older Adults: A Systematic Review and Meta-Analysis

Background: Recently, considerable research has been conducted to study the effects of transcranial direct current stimulation (tDCS) on balance control in older adults. We completed a comprehensive systematic review and meta-analysis to assess the efficacy of tDCS on balance control in this population. Methods: A search strategy based on the PICOS principle was used to find the literatures in the databases of PubMed, EMBASE, EBSCO, Web of Science. The quality and risk of bias in the studies were independently assessed by two researchers. Results: Ten studies were included in the systematic review. A meta-analysis was completed on six of these ten, with a total of 280 participants. As compared to sham (i.e., control), tDCS induced significant improvement with low heterogeneity in balance control in older adults. Specifically, tDCS induced large effects on the performance of the timed-up-and-go test, the Berg balance scale, and standing postural sway (e.g., sway area) and gait (e.g., walking speed) in dual task conditions (standardized mean differences (SMDs) = -0.99~3.41 95% confidence limits (CL): -1.52~4.50, p < 0.006, I 2 < 52%). Moderate-to-large effects of tDCS were also observed in the standing posture on a static or movable platform (SMDs = 0.37~1.12 95%CL: -0.09~1.62, p < 0.03, I 2 < 62%). Conclusion: Our analysis indicates that tDCS holds promise to promote balance in older adults. These results warrant future studies of larger sample size and rigorous study design and results report, as well as specific research to establish the relationship between the parameter of tDCS and the extent of tDCS-induced improvement in balance control in older adults.

Potential Biochemical Mechanisms of Brain Injury in Diabetes Mellitus

The goal of this review was to summarize current biochemical mechanisms of and risk factors for diabetic brain injury. We mainly summarized mechanisms published in the past three years and focused on diabetes induced cognitive impairment, diabetes-linked Alzheimer’s disease, and diabetic stroke. We think there is a need to conduct further studies with increased sample sizes and prolonged period of follow-ups to clarify the effect of DM on brain dysfunction. Additionally, we also think that enhancing experimental reproducibility using animal models in conjunction with application of advanced devices should be considered when new experiments are designed. It is expected that further investigation of the underlying mechanisms of diabetic cognitive impairment will provide novel insights into therapeutic approaches for ameliorating diabetes-associated injury in the brain.